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

US20140270489A1 LEARNED MID-LEVEL REPRESENTATION FOR CONTOUR AND OBJECT DETECTION 审中-公开
标题翻译：用于轮廓和对象检测的学习中级表示
公开(公告)号：US20140270489A1
公开(公告)日：2014-09-18
申请号：US13794857
申请日：2013-03-12
申请人： MICROSOFT CORPORATION
发明人： Joseph Jaewhan Lim , Piotr Dollar , Charles Lawrence Zitnick, III
IPC分类号： G06K9/62
CPC分类号： G06K9/6253 , G06K9/4604
摘要： Various technologies described herein pertain to constructing mid-level sketch tokens for use in tasks, such as object detection and contour detection. Sketch patches can be extracted from binary images that comprise hand-drawn contours. The hand-drawn contours in the binary images can correspond to contours in training images. The sketch patches can be clustered to form sketch token classes. Moreover, color patches from the training images can be extracted and low-level features of the color patches can be computed. Further, a classifier that labels mid-level sketch tokens can be trained. Such training of the classifier can be through supervised learning of a mapping from the low-level features of the color patches to the sketch token classes.
摘要翻译：本文描述的各种技术涉及构建用于任务的中级草图令牌，例如对象检测和轮廓检测。草图补丁可以从包含手绘轮廓的二进制图像中提取出来。二进制图像中的手绘轮廓可以对应于训练图像中的轮廓。草图修补程序可以聚类以形成草图标记类。此外，可以提取来自训练图像的色块，并且可以计算出色块的低级特征。此外，可以训练标记中级草图标记的分类器。分类器的这种训练可以通过从色标的低级特征到草图标记类的映射的监督学习。

2. 发明申请

US20140254926A1 ACCELERATING BITMAP REMOTING BY IDENTIFYING AND EXTRACTING 2D PATTERNS FROM SOURCE BITMAPS 有权
标题翻译：通过从源头鉴定和提取2D图案来加速比特币
公开(公告)号：US20140254926A1
公开(公告)日：2014-09-11
申请号：US14285794
申请日：2014-05-23
申请人： MICROSOFT CORPORATION
发明人： Nadim Y. Abdo , Voicu Anton Albu , Charles Lawrence Zitnick, III
IPC分类号： G06K9/46 , G06K9/18
CPC分类号： G06K9/4604 , G06K9/00463 , G06K9/00973 , G06K9/18 , G06K9/4652
摘要： Systems, methods and computer-readable storage media are disclosed for accelerating bitmap remoting by extracting non-grid tiles from source bitmaps. A server takes a source image, identifies possibly repetitive features, and tiles the image. For each tile that contains part of a possibly repetitive feature, the server replaces that part with the dominant color of the tile. The system then sends to a client a combination of new tiles and features, and indications to tiles and features that the client has previously received and stored, along with an indication of how to recreate the image based on the tiles and features.
摘要翻译：公开了用于通过从源位图提取非网格瓦片来加速位图远程处理的系统，方法和计算机可读存储介质。服务器采用源图像，识别可能的重复特征，并对图像进行平铺。对于包含可能重复功能的一部分的每个图块，服务器将该零件替换为图块的主要颜色。然后，系统向客户端发送新的瓦片和特征的组合，以及客户端先前已经接收和存储的瓦片和特征的指示，以及如何基于瓦片和特征重新创建图像的指示。

3. 发明授权

US08977060B2 Motion stabilization and detection of articulated objects 有权
标题翻译：运动稳定和铰接物体的检测
公开(公告)号：US08977060B2
公开(公告)日：2015-03-10
申请号：US13895964
申请日：2013-05-16
申请人： Microsoft Corporation
发明人： Piotr Dollar , Charles Lawrence Zitnick, III , Dennis I. Park
IPC分类号： G06K9/00 , H04N7/12 , H04N5/14 , G06T7/00
CPC分类号： G06K9/00711 , G06K9/00342 , G06T7/246
摘要： The techniques and systems described herein are directed to isolating part-centric motion in a visual scene and stabilizing (e.g., removing) motion in the visual scene that is associated with camera-centric motion and/or object-centric motion. By removing the motion that is associated with the camera-centric motion and/or the object-centric motion, the techniques are able to focus motion feature extraction mechanisms (e.g., temporal differencing) on the isolated part-centric motion. The extracted motion features may then be used to recognize and/or detect the particular type of object and/or estimate a pose or position of a particular type of object.
摘要翻译：本文描述的技术和系统旨在在视觉场景中隔离以部分为中心的运动，并且以与以摄像机为中心的运动和/或以对象为中心的运动相关联的视觉场景中的稳定（例如去除）运动。通过去除与以摄像机为中心的运动和/或以物体为中心的运动相关联的运动，这些技术能够将运动特征提取机制（例如，时间差分）聚焦在隔离的部分中心运动上。所提取的运动特征然后可用于识别和/或检测特定类型的对象和/或估计特定类型对象的姿势或位置。

4. 发明申请

US20140341474A1 MOTION STABILIZATION AND DETECTION OF ARTICULATED OBJECTS 有权
标题翻译：运动稳定和检测对象物体
公开(公告)号：US20140341474A1
公开(公告)日：2014-11-20
申请号：US13895964
申请日：2013-05-16
申请人： Microsoft Corporation
发明人： Piotr Dollar , Charles Lawrence Zitnick, III , Dennis I. Park
IPC分类号： G06T7/00
CPC分类号： G06K9/00711 , G06K9/00342 , G06T7/246
摘要： The techniques and systems described herein are directed to isolating part-centric motion in a visual scene and stabilizing (e.g., removing) motion in the visual scene that is associated with camera-centric motion and/or object-centric motion. By removing the motion that is associated with the camera-centric motion and/or the object-centric motion, the techniques are able to focus motion feature extraction mechanisms (e.g., temporal differencing) on the isolated part-centric motion. The extracted motion features may then be used to recognize and/or detect the particular type of object and/or estimate a pose or position of a particular type of object.
摘要翻译：本文描述的技术和系统旨在在视觉场景中隔离以部分为中心的运动，并且以与以摄像机为中心的运动和/或以对象为中心的运动相关联的视觉场景中的稳定（例如去除）运动。通过去除与以摄像机为中心的运动和/或以物体为中心的运动相关联的运动，这些技术能够将运动特征提取机制（例如，时间差分）聚焦在隔离的部分中心运动上。所提取的运动特征然后可用于识别和/或检测特定类型的对象和/或估计特定类型对象的姿势或位置。

5. 发明申请

US20150206319A1 DIGITAL IMAGE EDGE DETECTION 有权
标题翻译：数字图像边缘检测
公开(公告)号：US20150206319A1
公开(公告)日：2015-07-23
申请号：US14328506
申请日：2014-07-10
申请人： Microsoft Corporation
发明人： Piotr Dollar , Charles Lawrence Zitnick, III
IPC分类号： G06T7/00 , G06K9/62
CPC分类号： G06T7/13 , G06K9/4604 , G06K9/6296 , G06T2207/20081
摘要： Edges are detected in a digital image including a plurality of pixels. For each of the plurality of pixels, a plurality of different edge assessments are made for that pixel. Each different edge assessment considers that pixel in a different position of a different pixel patch. The different edge assessments for each pixel are aggregated.
摘要翻译：在包括多个像素的数字图像中检测边缘。对于多个像素中的每一个，针对该像素进行多个不同的边缘评估。每个不同的边缘评估认为像素在不同位置的不同像素补丁。每个像素的不同边缘评估被聚合。

6. 发明申请

US20140307058A1 ROBUST STEREO DEPTH SYSTEM 有权
标题翻译：可靠的立体声深度系统
公开(公告)号：US20140307058A1
公开(公告)日：2014-10-16
申请号：US13925762
申请日：2013-06-24
申请人： Microsoft Corporation
发明人： Adam G. Kirk , Oliver A. Whyte , Sing Bing Kang , Charles Lawrence Zitnick, III , Richard S. Szeliski , Shahram Izadi , Christoph Rhemann , Andreas Georgiou , Avronil Bhattacharjee
IPC分类号： H04N13/02 , H04N5/33
CPC分类号： G06K9/00536 , A63F13/213 , B29C64/00 , B29C64/386 , G01B11/22 , G01B11/25 , G01B11/2513 , G01B11/2527 , G01B11/2545 , G02B5/1895 , G02B27/4205 , G02B27/4233 , G02B27/44 , G06F3/0653 , G06F3/0659 , G06F3/0683 , G06F9/3004 , G06F9/30043 , G06F9/30127 , G06F11/3024 , G06F12/00 , G06F12/02 , G06F12/0207 , G06F12/0292 , G06K9/00201 , G06K9/0063 , G06K9/62 , G06T1/60 , G06T7/00 , G06T7/586 , G06T2207/30244 , H04N5/2256 , H04N5/33 , H04N5/332 , H04N9/045 , H04N13/128 , H04N13/239 , H04N13/25 , H04N13/254 , H04N13/271 , H04N17/002 , H04N2013/0081
摘要： The subject disclosure is directed towards a high resolution, high frame rate, robust stereo depth system. The system provides depth data in varying conditions based upon stereo matching of images, including actively illuminated IR images in some implementations. A clean IR or RGB image may be captured and used with any other captured images in some implementations. Clean IR images may be obtained by using a notch filter to filter out the active illumination pattern. IR stereo cameras, a projector, broad spectrum IR LEDs and one or more other cameras may be incorporated into a single device, which may also include image processing components to internally compute depth data in the device for subsequent output.
摘要翻译：主题公开涉及高分辨率，高帧率，鲁棒的立体深度系统。该系统基于图像的立体匹配，包括在一些实施中的主动照明的IR图像，在不同的条件下提供深度数据。在某些实现中，可以捕获干净的IR或RGB图像并与任何其他捕获的图像一起使用。清洁IR图像可以通过使用陷波滤波器来滤除有源照明图案来获得。红外立体照相机，投影仪，广谱红外LED和一个或多个其他相机可以并入到单个设备中，该设备还可以包括图像处理组件以在内部计算设备中的深度数据以用于随后的输出。

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