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

US07838814B2 Plenoptic system for recording images from sheets 有权
标题翻译：用于从纸张记录图像的辅助系统
公开(公告)号：US07838814B2
公开(公告)日：2010-11-23
申请号：US11805462
申请日：2007-05-23
申请人： Rajinderjeet Singh Minhas , Wencheng Wu , Robert P. Herloski
发明人： Rajinderjeet Singh Minhas , Wencheng Wu , Robert P. Herloski
IPC分类号： H01J3/14 , G06T15/10 , H04N9/47 , H04N5/235 , G06K9/00
CPC分类号： G02B26/0808 , G02B26/0875 , G02B26/105 , G02B26/106 , H04N1/1013 , H04N1/193 , H04N2201/0081 , H04N2201/02495 , H04N2201/0434 , H04N2201/0446
摘要： A system for recording an image as digital data comprises a photosensor array and a plenoptic set, including a main lens and a lenticular grating, to enable the photosensor array to obtain plenoptic image data from the sheet. A subset of the plenoptic image data is selected, such as according to a predetermined object distance, to obtain image data for a focused image. The subset of the plenoptic image can be selected after the scanning, so that prescanning of an unusual-shaped image-bearing object, such as an open book, is avoided.
摘要翻译：用于将图像记录为数字数据的系统包括光传感器阵列和包括主透镜和透镜光栅的全光组，以使光传感器阵列能够从片材获得全光图像数据。选择全光图像数据的子集，例如根据预定的对象距离，以获得聚焦图像的图像数据。可以在扫描之后选择全光图像的子集，从而避免对诸如打开的书的异常形状的图像承载对象的预扫描。

2. 发明申请

US20080291202A1 Plenoptic system for recording images from sheets 有权
标题翻译：用于从纸张记录图像的辅助系统
公开(公告)号：US20080291202A1
公开(公告)日：2008-11-27
申请号：US11805462
申请日：2007-05-23
申请人： Rajinderjeet Singh Minhas , Wencheng Wu , Robert P. Herloski
发明人： Rajinderjeet Singh Minhas , Wencheng Wu , Robert P. Herloski
IPC分类号： G06T15/20
CPC分类号： G02B26/0808 , G02B26/0875 , G02B26/105 , G02B26/106 , H04N1/1013 , H04N1/193 , H04N2201/0081 , H04N2201/02495 , H04N2201/0434 , H04N2201/0446
摘要： A system for recording an image as digital data comprises a photosensor array and a plenoptic set, including a main lens and a lenticular grating, to enable the photosensor array to obtain plenoptic image data from the sheet. A subset of the plenoptic image data is selected, such as according to a predetermined object distance, to obtain image data for a focused image. The subset of the plenoptic image can be selected after the scanning, so that prescanning of an unusual-shaped image-bearing object, such as an open book, is avoided.
摘要翻译：用于将图像记录为数字数据的系统包括光传感器阵列和包括主透镜和透镜光栅的全光组，以使光传感器阵列能够从片材获得全光图像数据。选择全光图像数据的子集，例如根据预定的对象距离，以获得聚焦图像的图像数据。可以在扫描之后选择全光图像的子集，从而避免对诸如打开的书的异常形状的图像承载对象的预扫描。

3. 发明申请

US20100325487A1 METHOD AND SYSTEM FOR AUTOMATICALLY DIAGNOSING FAULTS IN RENDERING DEVICES 有权
标题翻译：用于自动诊断渲染设备中的故障的方法和系统
公开(公告)号：US20100325487A1
公开(公告)日：2010-12-23
申请号：US12487803
申请日：2009-06-19
申请人： Rajinderjeet Singh Minhas , Vishal Monga , Wencheng Wu
发明人： Rajinderjeet Singh Minhas , Vishal Monga , Wencheng Wu
IPC分类号： G06F11/25 , G06N7/02
CPC分类号： G06F11/2257
摘要： A method and system for automatically determining an optimal re-training interval for a fault diagnoser based on online monitoring of the performance of a classifier. The classifier generates a soft measure of membership in association with a class based on a training data. The output of the classifier can be utilized to assign a label to new data and then the members associated with each class can be clustered into one or more core members and potential outliers. A statistical measure can be utilized to determine if the distribution of the outliers is sufficiently different than the core members after enough outliers have been accumulated. If the outliers are different with respect to the core members, then the diagnoser can be re-trained; otherwise, the output of the classifier can be fed to the fault diagnoser.
摘要翻译：一种用于基于在线监视分类器的性能来自动确定故障诊断器的最佳再训练间隔的方法和系统。分类器基于训练数据生成与类相关联的隶属度的软测量。分类器的输出可以用于为新数据分配标签，然后与每个类相关联的成员可以聚类成一个或多个核心成员和潜在的异常值。可以利用统计量度来确定离群点的分布是否充分地不同于核心成员在有足够的异常值累积之后。如果异常值与核心成员不同，那么诊断者可以重新训练; 否则，分类器的输出可以馈送给故障诊断器。

4. 发明授权

US08249830B2 Method and system for automatically diagnosing faults in rendering devices 有权
标题翻译：自动诊断渲染设备故障的方法和系统
公开(公告)号：US08249830B2
公开(公告)日：2012-08-21
申请号：US12487803
申请日：2009-06-19
申请人： Rajinderjeet Singh Minhas , Vishal Monga , Wencheng Wu , Divyanshu Vats
发明人： Rajinderjeet Singh Minhas , Vishal Monga , Wencheng Wu , Divyanshu Vats
IPC分类号： G21C17/00 , G06F11/30
CPC分类号： G06F11/2257
摘要： A method and system for automatically determining an optimal re-training interval for a fault diagnoser based on online monitoring of the performance of a classifier are disclosed. The classifier generates a soft measure of membership in association with a class based on a training data. The output of the classifier can be utilized to assign a label to new data and then the members associated with each class can be clustered into one or more core members and potential outliers. A statistical measure can be utilized to determine if the distribution of the outliers is sufficiently different than the core members after enough outliers have been accumulated. If the outliers are different with respect to the core members, then the diagnoser can be re-trained; otherwise, the output of the classifier can be fed to the fault diagnoser.
摘要翻译：公开了一种基于在线监视分类器的性能来自动确定故障诊断器的最佳再训练间隔的方法和系统。分类器基于训练数据生成与类相关联的隶属度的软测量。分类器的输出可以用于为新数据分配标签，然后与每个类相关联的成员可以聚类成一个或多个核心成员和潜在的异常值。可以利用统计量度来确定离群点的分布是否充分地不同于核心成员在有足够的异常值累积后。如果异常值与核心成员不同，那么诊断者可以重新训练; 否则，分类器的输出可以馈送给故障诊断器。

5. 发明授权

US10713499B2 Real-time video triggering for traffic surveillance and photo enforcement applications using near infrared video acquisition 有权
公开(公告)号：US10713499B2
公开(公告)日：2020-07-14
申请号：US13453089
申请日：2012-04-23
申请人： Wencheng Wu
发明人： Wencheng Wu
IPC分类号： G06K9/00 , G06K9/20 , G06K9/32 , H04N7/18
摘要： A method and system for real-time video triggering for traffic surveillance and photo enforcement comprises receiving a streaming video feed and performing a spatial uniformity correction on each frame of the streaming video feed and resampling the video feed to a lower spatial resolution. Motion blobs are then detected. Next a three-layered approach is used to identify candidate motion blobs which can be output to a triggering module to trigger a video collection action.

6. 发明授权

US09060164B2 Intelligent use of scene and test pattern analyses for traffic camera diagnostics 有权
标题翻译：智能使用场景和测试模式分析用于交通摄像机诊断
公开(公告)号：US09060164B2
公开(公告)日：2015-06-16
申请号：US13610907
申请日：2012-09-12
申请人： Wencheng Wu , Edul N. Dalal
发明人： Wencheng Wu , Edul N. Dalal
IPC分类号： H04N17/00 , G08G1/04
CPC分类号： H04N17/002 , G08G1/04
摘要： A method for determining a response to misalignment of a camera monitoring a desired area includes acquiring temporal related frames from the camera including a reference frame. A pixel location is determined of a reference object from the frames. Using the pixel location of the reference object, a displacement of the camera between a current frame and the reference frame is determined. For the displacement exceeding a first threshold, a new displacement of the camera is measured by introducing at least one additional object to a camera field of view and comparing the new displacement to a second threshold. For the new displacement not exceeding the second threshold, the camera is recalibrated using a determined pixel location and a physical location of the at least one additional object. For the new displacement exceeding the second threshold, notification is provided of a misalignment to an associated user device.
摘要翻译：用于确定对监视所需区域的相机的未对准的响应的方法包括从摄像机获取包括参考帧的时间相关帧。从帧中确定参考对象的像素位置。使用参考对象的像素位置，确定相机在当前帧与参考帧之间的位移。对于超过第一阈值的位移，通过将至少一个附加对象引入照相机视野并将新位移与第二阈值进行比较来测量照相机的新位移。对于不超过第二阈值的新位移，使用确定的像素位置和至少一个附加对象的物理位置来重新校准照相机。对于超过第二阈值的新位移，向相关联的用户设备通知未对准。

7. 发明授权

US09025024B2 System and method for object identification and tracking 有权
标题翻译：用于物体识别和跟踪的系统和方法
公开(公告)号：US09025024B2
公开(公告)日：2015-05-05
申请号：US13247343
申请日：2011-09-28
申请人： Beilei Xu , Wencheng Wu , Lalit Keshav Mestha , Graham Pennington
发明人： Beilei Xu , Wencheng Wu , Lalit Keshav Mestha , Graham Pennington
IPC分类号： H04N7/18 , G06K9/20 , H04N5/232 , H04N5/33
CPC分类号： G06K9/2018 , H04N5/23206 , H04N5/23219 , H04N5/332
摘要： What is disclosed is a system and method for identifying materials comprising an object captured in a video and for using the identified materials to track that object as it moves across the captured video scene. In one embodiment, a multi-spectral or hyper-spectral sensor is used to capture a spectral image of an object in an area of interest. Pixels in the spectral planes of the spectral images are analyzed to identify a material comprising objects in that area of interest. A location of each of the identified objects is provided to an imaging sensor which then proceeds to track the objects as they move through a scene. Various embodiments are disclosed.
摘要翻译：公开的是用于识别包括在视频中捕获的对象的材料的系统和方法，并且用于当所述对象在所捕获的视频场景中移动时使用所识别的材料来跟踪该对象。在一个实施例中，使用多光谱或超光谱传感器来捕获感兴趣区域中的对象的光谱图像。分析光谱图像的光谱平面中的像素以识别包含该感兴趣区域中的物体的材料。每个识别的对象的位置被提供给成像传感器，然后成像传感器在它们移动通过场景时跟踪对象。公开了各种实施例。

8. 发明授权

US08861023B2 Generating an unambiguous definition of designer intended colors in a document creation application 有权
标题翻译：在文档创建应用程序中生成设计者想要的颜色的明确定义
公开(公告)号：US08861023B2
公开(公告)日：2014-10-14
申请号：US13023822
申请日：2011-02-09
申请人： Edul N. Dalal , Wencheng Wu , Robert J. Rolleston
发明人： Edul N. Dalal , Wencheng Wu , Robert J. Rolleston
IPC分类号： H04N1/60 , H04N1/54 , H04N1/62
CPC分类号： H04N1/54 , H04N1/603 , H04N1/628
摘要： What is disclosed is a novel system and method for determining and capturing the designer intended colors in an image so that the printer has an accurate color rendition target. The present method operates by capturing the monitor RGB values together with the monitor profile to get a representation of the intended image in a device-independent color space like L*a*b*. The teachings hereof work for vector graphics as well as raster images. Advantageously, this invention solves a real problem currently existing, for example, in the packaging print market, wherein colors produced from multiple spot colors with their overlays and blends are not well color managed.
摘要翻译：公开的是用于确定和捕获图像中的设计者预期颜色的新型系统和方法，使得打印机具有准确的色彩再现目标。本方法通过将监视器RGB值与监视器配置文件一起捕获来操作，以在与设备无关的颜色空间（如L * a * b *）中获得所需图像的表示。这里的教学工作用于矢量图形以及光栅图像。有利地，本发明解决了例如在包装印刷市场中存在的真实问题，其中由具有它们的覆盖物和共混物的多种专色产生的颜色不是很好的颜色管理。

9. 发明授权

US08855436B2 System for and method of selective video frame compression and decompression for efficient event-driven searching in large databases 有权
标题翻译：选择性视频帧压缩和解压缩的系统和方法，用于大型数据库中高效的事件驱动搜索
公开(公告)号：US08855436B2
公开(公告)日：2014-10-07
申请号：US13277719
申请日：2011-10-20
申请人： Orhan Bulan , Edgar A. Bernal , Robert P. Loce , Wencheng Wu
发明人： Orhan Bulan , Edgar A. Bernal , Robert P. Loce , Wencheng Wu
IPC分类号： G06K9/36 , G06K9/46 , H04N19/107 , H04N19/172 , H04N19/139
CPC分类号： G08G1/0133 , G06K9/00785 , H04N19/107 , H04N19/139 , H04N19/172 , H04N19/513 , H04N19/61
摘要： A method of, and system for, selective video frame compression and decompression is presented. The disclosed technique is particularly suited for efficient event-driven searching in large databases. The technique involves designating certain frames in a video sequence as reference frames, to be compressed using a first compression technique, where the remaining frames are compressed using a second compression technique. The first compression technique may be implemented without requiring data from any neighboring frames.
摘要翻译：提出了选择性视频帧压缩和解压缩的方法和系统。所公开的技术特别适用于在大数据库中有效的事件驱动搜索。该技术涉及将视频序列中的某些帧指定为参考帧，以使用第一压缩技术进行压缩，其中使用第二压缩技术来压缩剩余的帧。可以实现第一压缩技术，而不需要来自任何相邻帧的数据。

10. 发明授权

US08797589B2 Color management and calibration using a scanner or camera 有权
标题翻译：使用扫描仪或相机进行颜色管理和校准
公开(公告)号：US08797589B2
公开(公告)日：2014-08-05
申请号：US12859760
申请日：2010-08-19
申请人： Edul N. Dalal , Wencheng Wu
发明人： Edul N. Dalal , Wencheng Wu
IPC分类号： G06K15/00 , G06F15/00 , H04N1/407 , H04N1/46 , G03F3/08
CPC分类号： H04N1/6033 , G01J3/462
摘要： A computer-implemented method for color calibration and profiling of an output device includes measuring a color patch in a test pattern, which comprises a plurality of color patches, to obtain first image data; measuring the color patch in the test pattern to obtain second image data; transforming the first image data to a first estimated image data; determining a difference between the second image data and the first estimated image data to obtain a correction factor; and calculating, for each patch in the test pattern, a corrected image data by applying the correction factor to a subsequent estimated image data from the first sensor. The correction factor is used for correcting inaccuracies introduced when the first image data is transformed into the first estimated image data. The first image data and the second image data provide a measured color representation of the color patch in a device dependent color space and a device independent color space, respectively.
摘要翻译：用于颜色校准和输出设备的轮廓的计算机实现的方法包括测量包括多个色块的测试图案中的色块以获得第一图像数据; 测量测试图案中的色块以获得第二图像数据; 将所述第一图像数据变换为第一估计图像数据; 确定第二图像数据和第一估计图像数据之间的差以获得校正因子; 以及通过将所述校正因子应用于来自所述第一传感器的后续估计图像数据来计算所述测试图案中的每个贴片的校正图像数据。校正因子用于校正当第一图像数据被变换为第一估计图像数据时引入的不精确度。第一图像数据和第二图像数据分别在设备依赖的颜色空间和设备独立的颜色空间中分别提供色标的测量的颜色表示。

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