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. 发明申请

WO2012092148A3 SCENE ACTIVITY ANALYSIS USING STATISTICAL AND SEMANTIC FEATURE LEARNT FROM OBJECT TRAJECTORY DATA 审中-公开
公开(公告)号：WO2012092148A3
公开(公告)日：2012-07-05
申请号：PCT/US2011/066962
申请日：2011-12-22
申请人： PELCO INC. , MILLAR, Greg , AGHDASI, Farzin , ZHU, Hongwei
发明人： MILLAR, Greg , AGHDASI, Farzin , ZHU, Hongwei
IPC分类号： G06T7/20 , H04N5/91 , H04N7/18
摘要： Trajectory information of objects appearing in a scene can be used to cluster trajectories into groups of trajectories according to each trajectory's relative distance between each other for scene activity analysis. By doing so, a database of trajectory data can be maintained that includes the trajectories to be clustered into trajectory groups. This database can be used to train a clustering system, and with extracted statistical features of resultant trajectory groups a new trajectory can be analyzed to determine whether the new trajectory is normal or abnormal. Embodiments described herein, can be used to determine whether a video scene is normal or abnormal. In the event that the new trajectory is identified as normal the new trajectory can be annotated with the extracted semantic data. In the event that the new trajectory is determined to be abnormal a user can be notified that an abnormal behavior has occurred.

2. 发明申请

WO2014151303A1 ONLINE LEARNING SYSTEM FOR PEOPLE DETECTION AND COUNTING 审中-公开
标题翻译：用于人员检测和计数的在线学习系统
公开(公告)号：WO2014151303A1
公开(公告)日：2014-09-25
申请号：PCT/US2014/025408
申请日：2014-03-13
申请人： PELCO, INC.
发明人： ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg , MITCHELL, Stephen, J.
IPC分类号： G06K9/00 , G06K9/62 , G06Q30/00
CPC分类号： G06K9/00369 , G06K9/00771 , G06K9/38 , G06K9/4642 , G06K9/6262 , G06K9/6267 , G06Q30/0201
摘要： People detection can provide valuable metrics that can be used by businesses, such as retail stores. Such information can be used to influence any number of business decisions such a employment hiring and product orders. The business value of this data hinges upon its accuracy. Thus, a method according to the principles of the current invention outputs metrics regarding people in a video frame within a stream of video frames through use of an object classifier configured to detect people. The method further comprises automatically updating the object classifier using data in at least a subset of the video frames in the stream of video frames.
摘要翻译：人员检测可以提供企业（例如零售商店）可以使用的有价值的指标。这些信息可用于影响任何数量的业务决策，如就业招聘和产品订单。该数据的业务价值取决于其准确性。因此，根据本发明的原理的方法通过使用被配置为检测人的对象分类器来输出视频帧内的视频帧中的人的度量。该方法还包括使用视频帧流中的视频帧的至少一个子集中的数据来自动更新对象分类器。

3. 发明申请

WO2013101866A1 METHOD AND SYSTEM FOR VIDEO CODING WITH NOISE FILTERING OF FOREGROUND OBJECT SEGMENTATION 审中-公开
标题翻译：用于前置对象分类的噪声滤波的视频编码方法和系统
公开(公告)号：WO2013101866A1
公开(公告)日：2013-07-04
申请号：PCT/US2012/071707
申请日：2012-12-27
申请人： PELCO, INC.
发明人： WANG, Lei , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G06T7/00
CPC分类号： H04N19/00 , G06T7/11 , G06T7/194 , G06T7/254 , G06T2207/20021 , G06T2207/20081 , H04N19/107 , H04N19/17 , H04N19/174 , H04N19/23
摘要： Techniques are discussed herein for providing mechanisms for coding and transmitting high definition video, e.g., over low bandwidth connections. In particular, foreground-objects are identified as distinct from the background of a scene represented by a plurality of video frames. In identifying foreground-objects, semantically significant and semantically insignificant movement (e.g., non- repetitive versus repetitive movement) is differentiated. For example, the swaying motion of a tree's leaves being minor and repetitive, can be determined to be semantically insignificant and to belong in a scene's background. Processing of the foreground-objects and background proceed at different update rates or frequencies. For example, foreground-objects can be updated 30 or 60 times per second. By contrast, a background is updated less frequently, e.g., once every 1 second or 10 seconds. In some implementations, if no foreground-objects are identified, no live video is transmitted (e.g., if no motion is detected, static images are not configured to be repeatedly sent). Techniques described herein take advantage of the realization that, in the area of surveillance and wireless communications, updating video of semantically significant movement at a high frame rate is sufficient.
摘要翻译：本文讨论了用于提供用于编码和传输高清晰度视频（例如，通过低带宽连接）的机制的技术。特别地，前景对象被识别为与由多个视频帧表示的场景的背景不同。在识别前景对象时，区分语义上重要的和语义上不显着的移动（例如，非重复性与重复运动）。例如，树叶的摇摆运动是小而重复的，可以被确定为语义上不重要，属于场景的背景。前景对象和背景的处理以不同的更新速率或频率进行。例如，前景对象可以每秒更新30或60次。相比之下，背景更不频繁地更新，例如每1秒或10秒一次。在一些实现中，如果没有识别出前景对象，则不发送实况视频（例如，如果没有检测到运动，静态图像不被配置为被重复发送）。本文描述的技术利用了以下认识：在监视和无线通信领域中，以高帧速率更新语义上显着的运动的视频是足够的。

4. 发明申请

WO2013101800A1 CAMERA CALIBRATION USING FEATURE IDENTIFICATION 审中-公开
标题翻译：使用特征识别的相机校准
公开(公告)号：WO2013101800A1
公开(公告)日：2013-07-04
申请号：PCT/US2012/071608
申请日：2012-12-26
申请人： PELCO, INC. , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
发明人： ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G06T7/00
CPC分类号： G06T7/0018 , G06T7/80 , G06T2207/10016 , G06T2207/20076 , G06T2207/30196 , G06T2207/30232 , G06T2207/30236
摘要： Disclosed are methods, systems, computer readable media and other implementations, including a method to calibrate a camera that includes capturing by the camera a frame of a scene, identifying features appearing in the captured frame, the features associated with pre-determined values representative of physical attributes of one or more objects, and determining parameters of the camera based on the identified features appearing in the captured frame and the pre-determined values associated with the identified features.
摘要翻译：公开了方法，系统，计算机可读介质和其他实施方式，包括校准相机的方法，其包括由相机拍摄场景的帧，识别出现在所捕获的帧中的特征，与代表一个或多个对象的物理属性，以及基于所捕获的帧中出现的所识别的特征以及与所识别的特征相关联的预定值来确定摄像机的参数。

5. 发明申请

WO2013095773A1 CLOUD-BASED VIDEO SURVEILLANCE MANAGEMENT SYSTEM 审中-公开
标题翻译：基于云的视频监控管理系统
公开(公告)号：WO2013095773A1
公开(公告)日：2013-06-27
申请号：PCT/US2012/062114
申请日：2012-10-26
申请人： PELCO, INC. , WANG, Lei , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
发明人： WANG, Lei , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G08B25/08 , G08B13/196
CPC分类号： G08B13/19671 , G08B13/19643 , G08B13/19645 , G08B13/19656 , H04N7/181 , H04N21/44008 , H04N21/4828 , H04N21/8133
摘要： An example of a system described herein includes a gateway (52) configured to obtain video content and metadata relating to the video content from a plurality of network devices (20, 42), a metadata processing module (82) communicatively coupled to the gateway (52) and configured to filter the metadata according to one or more criteria to obtain a filtered set of metadata, a video processing module (80) communicatively coupled to the gateway (52) and the metadata processing module (82) and configured to isolate video portions, of the video content, associated with respective first portions of the filtered set of metadata, and a cloud services interface (86) communicatively coupled to the gateway (52), the metadata processing module (82) and the video processing module (80) and configured to provide at least some of the filtered set of metadata or the isolated video portions to a cloud computing service (90).
摘要翻译：本文描述的系统的示例包括网关（52），其被配置为从多个网络设备（20,42）获得与视频内容相关的视频内容和元数据，元数据处理模块（82），通信地耦合到网关（并且被配置为根据一个或多个标准来过滤所述元数据以获得经过滤的集合的元数据，视频处理模块（80），其通信地耦合到所述网关（52）和所述元数据处理模块（82），并且被配置为隔离视频与所述经过滤的元数据集合的相应第一部分相关联的所述视频内容的部分，以及通信地耦合到所述网关（52）的云服务接口（86），所述元数据处理模块（82）和所述视频处理模块），并且被配置为向所述云计算服务（90）提供所述过滤的元数据集合或所述隔离视频部分中的至少一些。

6. 发明申请

WO2014081726A1 METHOD AND SYSTEM FOR METADATA EXTRACTION FROM MASTER-SLAVE CAMERAS TRACKING SYSTEM 审中-公开
标题翻译：用于从主从摄像机跟踪系统提取元数据的方法和系统
公开(公告)号：WO2014081726A1
公开(公告)日：2014-05-30
申请号：PCT/US2013/070807
申请日：2013-11-19
申请人： PELCO, INC.
发明人： HUANG, Chien-Min , AGHDASI, Farzin , ZHU, Hongwei , WANG, Lei , MA, Zhan Jiang
IPC分类号： H04N7/18 , G08B13/196
CPC分类号： H04N7/181 , G06K9/00771 , G06K9/209 , G06K9/6267 , G08B13/19608 , G08B13/19643 , G08B13/19671
摘要： An embodiment of the present invention includes a master camera that may record master metadata regarding an object of interest and communicate the master metadata to a slave camera. The slave camera may zoom, pan, or tilt to isolate and record more detailed image data regarding the object of interest based on the master metadata. In addition, the slave camera may record slave metadata regarding the object of interest. The master and slave metadata may be stored associated with the recorded image data enabling a later search for the object of interest to be expedited. The recorded image data including the object of interest may be identified with greater ease as it may be guided by the master or slave metadata, or a combination thereof. According to embodiments presented herein, processing time for searching and identifying an object of interest may be reduced by enabling a search on the metadata associated with image data, rather than by searching the image data itself.
摘要翻译：本发明的实施例包括可以记录关于感兴趣对象的主元数据并将主元数据传送到从照相机的主摄像机。从属照相机可以缩放，平移或倾斜以基于主元数据隔离并记录关于感兴趣对象的更详细的图像数据。此外，从属照相机可以记录关于感兴趣对象的从属元数据。主和从属元数据可以被存储与记录的图像数据相关联，使得能够加快对感兴趣对象的后续搜索。可以更容易地识别包括感兴趣对象的记录图像数据，因为它可以由主或从元数据或其组合来指导。根据本文呈现的实施例，可以通过对与图像数据相关联的元数据进行搜索而不是通过搜索图像数据本身来搜索和识别感兴趣对象的处理时间。

7. 发明申请

WO2014081688A1 METHOD AND APPARATUS FOR DETECTING PEOPLE BY A SURVEILLANCE SYSTEM 审中-公开
标题翻译：通过监测系统检测人的方法和装置
公开(公告)号：WO2014081688A1
公开(公告)日：2014-05-30
申请号：PCT/US2013/070691
申请日：2013-11-19
申请人： PELCO, INC.
发明人： ZHU, Hongwei , WANG, Lei , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G06K9/00 , G06K9/48
CPC分类号： G06K9/00362 , G06K9/00369 , G06K9/00771 , G06K9/34 , G06K9/48 , G06K9/6267
摘要： Surveillance systems may be found in both private and public spaces. In private spaces, they can be designed to help monitor secure premises. Similarly, public spaces may also use surveillance systems to determine an allocation of public resources. A camera surveillance system according to an embodiment of the invention uses advanced image processing techniques to determine whether an object moving across a scene is a person. The camera surveillance system achieves an accurate and efficient classification by selectively processing a set of features associated with the object, such as features that define an omega shape. By selectively processing the set of features associated with the object, the methods and systems described herein reduce the computational complexity of standard image processing/object detection techniques.
摘要翻译：监控系统可能在私人和公共场所都有。在私人空间内，他们可以设计成帮助监控安全场所。类似地，公共空间也可以使用监视系统来确定公共资源的分配。根据本发明的实施例的相机监视系统使用高级图像处理技术来确定跨场景移动的对象是否是人。相机监控系统通过选择性地处理与对象相关联的一组特征，例如定义Ω形的特征来实现精确和有效的分类。通过选择性地处理与对象相关联的特征集合，本文描述的方法和系统降低了标准图像处理/对象检测技术的计算复杂度。

8. 发明申请

WO2013103591A1 CONTEXT AWARE MOVING OBJECT DETECTION 审中-公开
标题翻译：背景知识移动物体检测
公开(公告)号：WO2013103591A1
公开(公告)日：2013-07-11
申请号：PCT/US2012/071967
申请日：2012-12-28
申请人： PELCO, INC. , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg , WANG, Lei
发明人： ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg , WANG, Lei
IPC分类号： G06T7/20
CPC分类号： G06T7/2053 , G06T7/254 , G06T2207/10016 , G06T2207/30196 , G06T2207/30232
摘要： An image capture system includes: an image capture unit configured to capture a first image frame comprising a set of pixels; and a processor coupled to the image capture unit and configured to: determine a normalized distance of a pixel characteristic between the first image frame and a second image frame for each pixel in the first image frame; compare the normalized distance for each pixel in the first image frame against a pixel sensitivity value for that pixel; determine that a particular pixel of the first image frame is a foreground or background pixel based on the normalized distance of the particular pixel relative to the pixel sensitivity value for the particular pixel; and adapt the pixel sensitivity value for each pixel over a range of allowable pixel sensitivity values.
摘要翻译：图像拍摄系统包括：图像拍摄单元，被配置为捕获包括一组像素的第一图像帧; 以及处理器，其耦合到所述图像捕获单元并且被配置为：确定所述第一图像帧中的每个像素的所述第一图像帧和第二图像帧之间的像素特性的归一化距离; 将第一图像帧中的每个像素的归一化距离与该像素的像素灵敏度值进行比较; 基于特定像素相对于特定像素的像素灵敏度值的归一化距离，确定第一图像帧的特定像素是前景或背景像素; 并且在允许的像素灵敏度值的范围内适应每个像素的像素灵敏度值。

9. 发明申请

WO2013101460A2 CLUSTERING-BASED OBJECT CLASSIFICATION 审中-公开
标题翻译：基于聚类的对象分类
公开(公告)号：WO2013101460A2
公开(公告)日：2013-07-04
申请号：PCT/US2012/069148
申请日：2012-12-12
申请人： PELCO, INC. , ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
发明人： ZHU, Hongwei , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G06K9/68
CPC分类号： G06K9/68
摘要： An example of a method for identifying objects in video content according to the disclosure includes receiving video content of a scene captured by a video camera, detecting an object in the video content, identifying a track that the object follows over a series of frames of the video content, extracting object features for the object from the video content, and classifying the object based on the object features. Classifying the object further comprises: determining a track-level classification for the object using spatially invariant object features, determining a global-clustering classification for the object using spatially variant features, and determining an object type for the object based on the track-level classification and the global-clustering classification for the object.
摘要翻译：根据本公开的用于识别视频内容中的对象的方法的示例包括：接收由摄像机捕获的场景的视频内容;检测视频内容中的对象;识别对象跟随视频内容的一系列帧，从视频内容中提取对象的对象特征，并基于对象特征对对象进行分类。对对象进行分类还包括：使用空间不变对象特征确定对象的轨迹级分类，使用空间变化特征确定对象的全局聚类分类，以及基于轨迹级分类确定对象的对象类型以及该对象的全局聚类分类。

10. 发明申请

WO2012092150A2 INFERENCE ENGINE FOR VIDEO ANALYTICS METADATA-BASED EVENT DETECTION AND FORENSIC SEARCH 审中-公开
标题翻译：用于视频分析的信号发动机基于元数据的事件检测和威尔逊搜索
公开(公告)号：WO2012092150A2
公开(公告)日：2012-07-05
申请号：PCT/US2011/066974
申请日：2011-12-22
申请人： PELCO INC. , ZHU, Hongwei , WANG, Lei , YANG, Shu , AGHDASI, Farzin , MILLAR, Greg
发明人： ZHU, Hongwei , WANG, Lei , YANG, Shu , AGHDASI, Farzin , MILLAR, Greg
IPC分类号： G06K9/46 , G06T7/00
CPC分类号： H04N21/4828 , G06F17/3079 , G06F17/30817 , G06F17/30828 , G06F17/30834 , G06K9/00771 , H04N5/76
摘要： Embodiments of the disclosure provide for systems and methods for searching video data for events and/or behaviors. An inference engine can be used to aide in the searching. In some embodiments, a user can specify various search criteria, for example, a video source(s), an event(s) or behavior(s) to search, and an action(s) to perform in the event of a successful search. The search can be performed by analyzing an object(s) found within scenes of the video data. An object can be identified by a number of attributes specified by the user. Once the search criteria has been received from the user, the video data can be received (or extracted from storage), the data analyzed for the specified events (or behaviors), and the specified action performed in the event a successful search occurs.
摘要翻译：本公开的实施例提供了用于搜索视频数据以用于事件和/或行为的系统和方法。推理引擎可以用于辅助搜索。在一些实施例中，用户可以指定各种搜索标准，例如视频源，要搜索的事件或行为，以及在成功搜索的情况下执行的动作。可以通过分析在视频数据的场景内发现的对象来执行搜索。对象可以由用户指定的多个属性来标识。一旦从用户接收到搜索条件，就可以接收（或从存储中提取）视频数据，分析指定事件（或行为）的数据，以及在发生成功搜索的情况下执行的指定动作。

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