公开(公告)号：US20130286208A1

公开(公告)日：2013-10-31

申请号：US13476239

申请日：2012-05-21

申请人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

发明人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

IPC分类号： H04N7/18

CPC分类号： G06K9/00771 ,  G06K9/6249 ,  G08G1/0129 ,  H04N7/181

摘要： Methods and systems for automatically detecting multi-object anomalies at a traffic intersection utilizing a joint sparse reconstruction model. A first input video sequence at a first traffic location can be received and at least one normal event involving P moving objects (where P is greater than or equal to 1) can be identified in an offline training phase. The normal event in the first input video sequence can be assigned to at least one normal event class and a training dictionary suitable for joint sparse reconstruction can be built in the offline training phase. A second input video sequence captured at a second traffic location similar to the first traffic location can be received and at least one event involving P moving objects can be identified in an online detection phase.

摘要翻译： 利用联合稀疏重建模型自动检测交通路口多物体异常的方法和系统。 可以在离线训练阶段中识别在第一交通位置处的第一输入视频序列，并且可以在离线训练阶段识别涉及P个运动对象（其中P大于或等于1）的至少一个正常事件。 可以将第一输入视频序列中的正常事件分配给至少一个正常事件类，并且可以在离线训练阶段中构建适合关联稀疏重建的训练字典。 可以接收在类似于第一业务位置的第二业务位置处捕获的第二输入视频序列，并且可以在在线检测阶段中识别涉及P个移动对象的至少一个事件。

公开(公告)号：US09710727B2

公开(公告)日：2017-07-18

申请号：US13773097

申请日：2013-02-21

申请人： Raja Bala ,  Vishal Monga ,  Xuan Mo ,  Zhigang Fan

发明人： Raja Bala ,  Vishal Monga ,  Xuan Mo ,  Zhigang Fan

IPC分类号： G06K9/62 ,  G06K9/00

CPC分类号： G06K9/6256 ,  G06K9/00771 ,  G06K9/6249

摘要： A method and system for detecting anomalies in video footage. A training dictionary can be configured to include a number of event classes, wherein events among the event classes can be defined with respect to n-dimensional feature vectors. One or more nonlinear kernel function can be defined, which transform the n-dimensional feature vectors into a higher dimensional feature space. One or more test events can then be received within an input video sequence of the video footage. Thereafter, a determination can be made if the test event(s) is anomalous by applying a sparse reconstruction with respect to the training dictionary in the higher dimensional feature space induced by the nonlinear kernel function.

公开(公告)号：US20140232862A1

公开(公告)日：2014-08-21

申请号：US13773097

申请日：2013-02-21

申请人： Raja Bala ,  Vishal Monga ,  Xuan Mo ,  Zhigang Fan

发明人： Raja Bala ,  Vishal Monga ,  Xuan Mo ,  Zhigang Fan

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/00771 ,  G06K9/6249

摘要： A method and system for detecting anomalies in video footage. A training dictionary can be configured to include a number of event classes, wherein events among the event classes can be defined with respect to n-diminensional feature vectors. One or more nonlinear kernel function can be defined, which transform the n-dimensional feature vectors into a higher dimensional feature space. One or more test events can then be received within an input video sequence of the video footage. Thereafter, a determination can be made if the test event(s) is anomalous by applying a sparse reconstruction with respect to the training dictionary in the higher dimensional feature space induced by the nonlinear kernel function.

摘要翻译： 一种用于检测视频画面异常的方法和系统。 训练词典可以被配置为包括多个事件类，其中事件类中的事件可以相对于n维特征向量来定义。 可以定义一个或多个非线性内核函数，其将n维特征向量变换成更高维度的特征空间。 然后可以在视频录像的输入视频序列内接收一个或多个测试事件。 此后，如果通过对由非线性内核函数引起的较高维特征空间中的训练词典应用稀疏重建来测试事件是异常的，则可以进行确定。

公开(公告)号：US09122932B2

公开(公告)日：2015-09-01

申请号：US13476239

申请日：2012-05-21

申请人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

发明人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

IPC分类号： H04N7/18 ,  G06K9/00 ,  G08G1/01 ,  G06K9/62

CPC分类号： G06K9/00771 ,  G06K9/6249 ,  G08G1/0129 ,  H04N7/181

摘要： Methods and systems for automatically detecting multi-object anomalies at a traffic intersection utilizing a joint sparse reconstruction model. A first input video sequence at a first traffic location can be received and at least one normal event involving P moving objects (where P is greater than or equal to 1) can be identified in an offline training phase. The normal event in the first input video sequence can be assigned to at least one normal event class and a training dictionary suitable for joint sparse reconstruction can be built in the offline training phase. A second input video sequence captured at a second traffic location similar to the first traffic location can be received and at least one event involving P moving objects can be identified in an online detection phase.

摘要翻译： 利用联合稀疏重建模型自动检测交通路口多物体异常的方法和系统。 可以在离线训练阶段中识别在第一交通位置处的第一输入视频序列，并且可以在离线训练阶段识别涉及P个运动对象（其中P大于或等于1）的至少一个正常事件。 可以将第一输入视频序列中的正常事件分配给至少一个正常事件类，并且可以在离线训练阶段中构建适合关联稀疏重建的训练字典。 可以接收在类似于第一业务位置的第二业务位置处捕获的第二输入视频序列，并且可以在在线检测阶段中识别涉及P个移动对象的至少一个事件。

公开(公告)号：US20130286198A1

公开(公告)日：2013-10-31

申请号：US13455687

申请日：2012-04-25

申请人： Zhigang Fan ,  Raja Bala ,  Xuan Mo

发明人： Zhigang Fan ,  Raja Bala ,  Xuan Mo

IPC分类号： H04N7/18

CPC分类号： G06K9/00785 ,  G08G1/04

摘要： A method, system and processor-readable medium for automatically detecting anomalies at a traffic intersection. A set of clusters of nominal vehicle paths and a set of clusters of nominal trajectories within the nominal vehicle paths can be derived in an offline process. A set of features within each nominal trajectory among the set of clusters of nominal trajectories can be selected. A probability distribution for features indicative of nominal vehicle behavior within the nominal trajectories can be derived. An input video sequence can be received and presence of the anomaly in the vehicle path, trajectories and features within the input video sequence can be detected utilizing the derived path clusters, trajectory clusters, and feature distributions.

摘要翻译： 一种用于自动检测交通路口异常的方法，系统和处理器可读介质。 在离线过程中可以导出一组标称车辆路径的群集和名义车辆路径中的一组标称轨迹。 可以选择在标称轨迹集合中的每个标称轨迹内的一组特征。 可以推导出在标称轨迹内指示车辆行为名义的特征的概率分布。 可以接收输入视频序列，并且可以使用导出的路径簇，轨迹簇和特征分布来检测输入视频序列内的车辆路径，轨迹和特征中的异常的存在。