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

US08532390B2 Semantic parsing of objects in video 有权
标题翻译：视频中对象的语义解析
公开(公告)号：US08532390B2
公开(公告)日：2013-09-10
申请号：US12845095
申请日：2010-07-28
申请人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel André Vaquero
发明人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel André Vaquero
IPC分类号： G06K9/00
CPC分类号： G06K9/00718 , G06K9/00369 , G06K9/00664 , G06K9/469 , G06K9/6201 , G06K9/6202 , G06K9/6232 , G06K9/6857
摘要： The invention provides an improved method to detect semantic attributes of human body in computer vision. In detecting semantic attributes of human body in computer vision, the invention maintains a list of semantic attributes, each of which corresponds to a human body part. A computer module then analyzes segments of a frame of a digital video to detect each semantic attribute by finding a most likely attribute for each segment. A threshold is applied to select candidate segments of the frame for further analysis. The candidate segments of the frame then go through geometric and resolution context analysis by applying the physical structure principles of a human body and by analyzing increasingly higher resolution versions of the image to verify the existence and accuracy of parts and attributes. A computer module computes a resolution context score for a lower resolution version of the image based on a weighted average score computed for a higher resolution version of the image by evaluating appearance features, geometric features, and resolution context features when available on the higher resolution version of the image. Finally, an optimal configuration step is performed via dynamic programming to select an optimal output with both semantic attributes and spatial positions of human body parts on the frame.
摘要翻译：本发明提供了一种用于检测计算机视觉中人体语义属性的改进方法。在检测计算机视觉中人体的语义属性时，本发明保留了语义属性的列表，每个语义属性对应于人体部分。然后，计算机模块通过为每个段找到最可能的属性来分析数字视频的帧的段以检测每个语义属性。应用阈值来选择帧的候选片段用于进一步分析。然后，帧的候选片段通过应用人体的物理结构原理并通过分析图像的越来越高的分辨率版本来验证部件和属性的存在和准确性来进行几何和分辨率上下文分析。计算机模块基于通过在更高分辨率版本上可用时评估外观特征，几何特征和分辨率上下文特征来计算针对图像的较高分辨率版本的加权平均得分，来计算图像的较低分辨率版本的分辨率上下文得分的图像。最后，通过动态规划执行最佳配置步骤，以选择具有框架上人体部位的语义属性和空间位置的最优输出。

2. 发明授权

US08483490B2 Calibration of video object classification 有权
标题翻译：视频对象分类校准
公开(公告)号：US08483490B2
公开(公告)日：2013-07-09
申请号：US12200059
申请日：2008-08-28
申请人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
发明人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6267 , G06K9/00369 , G06K9/00771 , G06K9/2081 , G06K9/3241 , G06K2209/23
摘要： Techniques for calibrating a classification system, wherein one or more objects in at least one video are classified, are provided. At least one view associated with the at least one video is obtained. The at least one view is partitioned into at least one region. A given object is classified in accordance with its location in reference to the at least one region. In an additional embodiment, one or more object models are obtained. At least one normalized size of the one or more objects is defined within at least one view associated with the at least one video in accordance with the one or more object models. The one or more objects are classified in accordance with the at least one defined normalized size.
摘要翻译：提供了一种用于校准分类系统的技术，其中至少一个视频中的一个或多个对象被分类。获得与至少一个视频相关联的至少一个视图。至少一个视图被划分为至少一个区域。给定对象根据其位置参照至少一个区域进行分类。在另外的实施例中，获得一个或多个对象模型。根据一个或多个对象模型，在与至少一个视频相关联的至少一个视图内定义一个或多个对象的至少一个归一化大小。根据至少一个定义的归一化尺寸对一个或多个对象进行分类。

3. 发明授权

US08249301B2 Video object classification 有权
标题翻译：视频对象分类
公开(公告)号：US08249301B2
公开(公告)日：2012-08-21
申请号：US12200017
申请日：2008-08-28
申请人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
发明人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/00369 , G06K9/00771 , G06K9/2081 , G06K9/3241 , G06K2209/23
摘要： Techniques for classifying one or more objects in at least one video, wherein the at least one video comprises a plurality of frames are provided. One or more objects in the plurality of frames are tracked. A level of deformation is computed for each of the one or more tracked objects in accordance with at least one change in a plurality of histograms of oriented gradients for a corresponding tracked object. Each of the one or more tracked objects is classified in accordance with the computed level of deformation.
摘要翻译：用于对至少一个视频中的一个或多个对象进行分类的技术，其中所述至少一个视频包括多个帧。跟踪多个帧中的一个或多个对象。根据对应的跟踪对象的定向梯度的多个直方图中的至少一个变化来计算一个或多个跟踪对象中的每一个的变形水平。一个或多个跟踪物体中的每一个根据计算的变形水平进行分类。

4. 发明授权

US07777615B2 System for assisting the attachment of a trailer to a vehicle 失效
标题翻译：用于协助将拖车附接到车辆的系统
公开(公告)号：US07777615B2
公开(公告)日：2010-08-17
申请号：US12052115
申请日：2008-03-20
申请人： Masato Okuda , Christian Arthur Trager , Lisa Marie Brown , Michael Wiegand , Tanemichi Chiba , Christopher Kurpinski , Jeffrey Edward Angeliu , Hirohiko Yanagawa , Yoshihisa Sato , Toshihiro Wakamatsu , Justin McBride , Thomas Keeling
发明人： Masato Okuda , Christian Arthur Trager , Lisa Marie Brown , Michael Wiegand , Tanemichi Chiba , Christopher Kurpinski , Jeffrey Edward Angeliu , Hirohiko Yanagawa , Yoshihisa Sato , Toshihiro Wakamatsu , Justin McBride , Thomas Keeling
IPC分类号： G08B21/00
CPC分类号： B60D1/36
摘要： A system for assisting the alignment of a hitch pin mounted on the rear of a vehicle with a hitch socket mounted on the front of a trailer. The system includes a camera mounted to the vehicle and positioned to capture an image rearwardly of the vehicle. A video display is contained within the vehicle which displays the image captured by the camera. A processor is also contained in the vehicle which calculates a preferred path of travel of the vehicle to position the hitch pin in alignment with the hitch socket. The processor is programmed to provide instructions to an operator of the vehicle of the required steering to maintain the vehicle on the preferred path of travel. The processor recalculates the preferred path of travel whenever the vehicle veers from the preferred path of travel by a preset threshold.
摘要翻译：一种用于辅助安装在车辆后部的搭扣销的对准的系统与安装在拖车前部的搭接插座。该系统包括安装到车辆并被定位成捕获车辆后方的图像的照相机。视频显示器包含在车辆内，其显示由相机拍摄的图像。车辆中还包含处理器，其计算车辆行驶的优选路径以将搭扣销定位成与搭接插座对准。处理器被编程为向车辆的操作者提供所需转向的指令，以将车辆保持在优选的行进路径上。当车辆从优选的行进路线偏离预设阈值时，处理器重新计算首选行驶路径。

5. 发明授权

US07529388B2 Methods for automatically tracking moving entities entering and exiting a specified region 有权
标题翻译：自动跟踪进入和离开指定区域的移动实体的方法
公开(公告)号：US07529388B2
公开(公告)日：2009-05-05
申请号：US12115186
申请日：2008-05-05
申请人： Lisa Marie Brown , Arun Hampapur , Andrew William Senior , Ying Li Tian , Senem Velipasalar
发明人： Lisa Marie Brown , Arun Hampapur , Andrew William Senior , Ying Li Tian , Senem Velipasalar
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/32 , G06K9/00778 , G06T7/246 , G06T2207/30241
摘要： Techniques for tracking entities using a single overhead camera are provided. A foreground region is detected in a video frame of the single overhead camera corresponding to one or more entities. It is determined if the foreground region is associated with an existing tracker. It is determined whether the detected foreground region is the result of at least one of a merger of two or more smaller foreground regions having corresponding existing trackers and a split of a larger foreground region having a corresponding existing tracker when the detected foreground region is not associated with an existing tracker. The detected foreground region is tracked via at least one existing tracker when the foreground region is associated with an existing tracker or the foreground region is the result of at least one of a merger and a split.
摘要翻译：提供了使用单个架空照相机跟踪实体的技术。在对应于一个或多个实体的单个架空摄像机的视频帧中检测到前景区域。确定前景区域是否与现有跟踪器相关联。确定检测到的前景区域是否是具有对应的现有跟踪器的两个或更多个更小的前景区域的合并中的至少一个的结果，以及当检测到的前景区域不相关联时具有相应的现有跟踪器的较大前景区域的分割的结果与现有的跟踪器。当前景区域与现有的跟踪器相关联时，经过至少一个现有跟踪器跟踪检测到的前景区域，或者前景区域是合并和拆分中的至少一个的结果。

6. 发明申请

US20090067716A1 Robust and efficient foreground analysis for real-time video surveillance 失效
公开(公告)号：US20090067716A1
公开(公告)日：2009-03-12
申请号：US11039442
申请日：2005-01-20
申请人： Lisa Marie Brown , Arun Hampapur , Zuoxuan Lu , Andrew William Senior , Ying-Li Tian
发明人： Lisa Marie Brown , Arun Hampapur , Zuoxuan Lu , Andrew William Senior , Ying-Li Tian
IPC分类号： G06K9/34
CPC分类号： G06K9/38 , G06K9/00597 , G06K9/00771
摘要： Systems and methods for foreground analysis in real-time video include background subtraction and foreground detection, shadow removal, quick lighting change adaptation, static foreground region detection, foreground fragment reduction, and frame level change detection. Processes include background image extraction and foreground detection, integrating texture information of the background image and a current frame to remove false positive foreground areas resulting from lighting changes, integrating pixel intensity information by determining a cross-correlation of intensities between a current frame and the background image for each pixel in a foreground mask to remove image shadows. Static foreground region detection and fragment reduction are also included.

7. 发明授权

US07468662B2 Method for spatio-temporal event detection using composite definitions for camera systems 有权
标题翻译：用于相机系统的复合定义的时空事件检测方法
公开(公告)号：US07468662B2
公开(公告)日：2008-12-23
申请号：US11455210
申请日：2006-06-16
申请人： Senem Velipasalar , Lisa Marie Brown , Arun Hampapur , Chiao-Fe Shu
发明人： Senem Velipasalar , Lisa Marie Brown , Arun Hampapur , Chiao-Fe Shu
IPC分类号： G08B13/00 , H04N7/18
CPC分类号： H04N7/18 , G08B13/19615 , G08B13/19645 , G08B13/1968 , G08B13/19693 , G08B13/19697
摘要： A method for monitoring events includes defining alert events based on primitive event types in an environment monitored by monitoring devices. Alert parameters are set for each alert event, and alert events are combined to create a composite alert event based on a plurality of alert events. A plurality of engines is monitored to determine if multiple events comprising the composite alert event have occurred.
摘要翻译：用于监视事件的方法包括基于由监视设备监视的环境中的基本事件类型定义警报事件。为每个警报事件设置警报参数，并且组合警报事件以基于多个警报事件来创建组合警报事件。监视多个引擎以确定是否已经发生了包括复合警报事件的多个事件。

8. 发明授权

US08289392B2 Automatic multiscale image acquisition from a steerable camera 失效
标题翻译：从可控照相机进行自动多尺度图像采集
公开(公告)号：US08289392B2
公开(公告)日：2012-10-16
申请号：US12166732
申请日：2008-07-02
申请人： Andrew William Senior , Sharathchandra Pankanti , Arun Hampapur , Lisa Marie Brown , Ying-Li Tian
发明人： Andrew William Senior , Sharathchandra Pankanti , Arun Hampapur , Lisa Marie Brown , Ying-Li Tian
IPC分类号： H04N7/18
CPC分类号： H04N5/232 , H04N5/23216 , H04N5/247 , H04N7/18
摘要： A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.
摘要翻译：提供了一种用于通过将俯仰变焦相机瞄准在固定摄像机视图中检测到的目标来自动获取高分辨率图像的系统。该系统使用多台摄像机之间的自动或手动校准。使用自动校准，估计初始位置的摄像机之间的单应性以及平移和倾斜控制的影响以及人物在图像中的预期高度。这些校准被链接在一起以引导从照相机。手动校准方案将相机引导到所需的感兴趣区域，并相应地计算平移，平铺和缩放参数。

9. 发明授权

US07796154B2 Automatic multiscale image acquisition from a steerable camera 有权
标题翻译：从可控照相机进行自动多尺度图像采集
公开(公告)号：US07796154B2
公开(公告)日：2010-09-14
申请号：US11074383
申请日：2005-03-07
申请人： Andrew William Senior , Sharathchandra Pankanti , Arun Hampapur , Lisa Marie Brown , Ying-Li Tian
发明人： Andrew William Senior , Sharathchandra Pankanti , Arun Hampapur , Lisa Marie Brown , Ying-Li Tian
IPC分类号： H04N7/18
CPC分类号： H04N5/232 , H04N5/23216 , H04N5/247 , H04N7/18
摘要： A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.
摘要翻译：提供了一种用于通过将俯仰变焦相机瞄准在固定摄像机视图中检测到的目标来自动获取高分辨率图像的系统。该系统使用多台摄像机之间的自动或手动校准。使用自动校准，估计初始位置的摄像机之间的单应性以及平移和倾斜控制的效果以及人物在图像中的预期高度。这些校准被链接在一起以引导从照相机。手动校准方案将相机引导到所需的感兴趣区域，并相应地计算平移，平铺和缩放参数。

10. 发明申请

US20100054535A1 Video Object Classification 有权
标题翻译：视频对象分类
公开(公告)号：US20100054535A1
公开(公告)日：2010-03-04
申请号：US12200017
申请日：2008-08-28
申请人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
发明人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
IPC分类号： G06K9/62
CPC分类号： G06K9/00369 , G06K9/00771 , G06K9/2081 , G06K9/3241 , G06K2209/23
摘要： Techniques for classifying one or more objects in at least one video, wherein the at least one video comprises a plurality of frames are provided. One or more objects in the plurality of frames are tracked. A level of deformation is computed for each of the one or more tracked objects in accordance with at least one change in a plurality of histograms of oriented gradients for a corresponding tracked object. Each of the one or more tracked objects is classified in accordance with the computed level of deformation.
摘要翻译：用于对至少一个视频中的一个或多个对象进行分类的技术，其中所述至少一个视频包括多个帧。跟踪多个帧中的一个或多个对象。根据对应的跟踪对象的定向梯度的多个直方图中的至少一个变化来计算一个或多个跟踪对象中的每一个的变形水平。一个或多个跟踪物体中的每一个根据计算的变形水平进行分类。

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