-
公开(公告)号：US09123144B2
公开(公告)日：2015-09-01
申请号：US13295009
申请日：2011-11-11
申请人： Nikolay Smolyanskiy , Christian F. Huitema , Cha Zhang , Lin Liang , Sean Eron Anderson , Zhengyou Zhang
发明人： Nikolay Smolyanskiy , Christian F. Huitema , Cha Zhang , Lin Liang , Sean Eron Anderson , Zhengyou Zhang
CPC分类号： G06T7/20 , G06K9/00 , G06T7/579 , G06T13/20 , G06T17/00 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/30201
摘要： A three-dimensional shape parameter computation system and method for computing three-dimensional human head shape parameters from two-dimensional facial feature points. A series of images containing a user's face is captured. Embodiments of the system and method deduce the 3D parameters of the user's head by examining a series of captured images of the user over time and in a variety of head poses and facial expressions, and then computing an average. An energy function is constructed over a batch of frames containing 2D face feature points obtained from the captured images, and the energy function is minimized to solve for the head shape parameters valid for the batch of frames. Head pose parameters and facial expression and animation parameters can vary over each captured image in the batch of frames. In some embodiments this minimization is performed using a modified Gauss-Newton minimization technique using a single iteration.
摘要翻译： 一种用于从二维面部特征点计算三维人头形状参数的三维形状参数计算系统和方法。 捕获包含用户脸部的一系列图像。 系统和方法的实施例通过随时间和各种头部姿势和面部表情检查用户的一系列捕获图像，然后计算平均值来推导用户头部的3D参数。 在包含从捕获图像获得的2D面部特征点的一批帧上构建能量函数，并且将能量函数最小化以解决对于批次帧有效的头部形状参数。 头部姿势参数和面部表情和动画参数可以在批次帧中的每个拍摄图像上变化。 在一些实施例中，使用使用单次迭代的修正的高斯 - 牛顿最小化技术来执行该最小化。
-
公开(公告)号：US20130121526A1
公开(公告)日：2013-05-16
申请号：US13295009
申请日：2011-11-11
申请人： Nikolay Smolyanskiy , Christian F. Huitema , Cha Zhang , Lin Liang , Sean Eron Anderson , Zhengyou Zhang
发明人： Nikolay Smolyanskiy , Christian F. Huitema , Cha Zhang , Lin Liang , Sean Eron Anderson , Zhengyou Zhang
IPC分类号： G06K9/00
CPC分类号： G06T7/20 , G06K9/00 , G06T7/579 , G06T13/20 , G06T17/00 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/30201
摘要： A three-dimensional shape parameter computation system and method for computing three-dimensional human head shape parameters from two-dimensional facial feature points. A series of images containing a user's face is captured. Embodiments of the system and method deduce the 3D parameters of the user's head by examining a series of captured images of the user over time and in a variety of head poses and facial expressions, and then computing an average. An energy function is constructed over a batch of frames containing 2D face feature points obtained from the captured images, and the energy function is minimized to solve for the head shape parameters valid for the batch of frames. Head pose parameters and facial expression and animation parameters can vary over each captured image in the batch of frames. In some embodiments this minimization is performed using a modified Gauss-Newton minimization technique using a single iteration.
-
公开(公告)号：US09148637B2
公开(公告)日：2015-09-29
申请号：US13288964
申请日：2011-11-04
CPC分类号： H04N9/735 , G06F3/011 , G06F3/017 , G06K9/00201 , G06K9/00234 , G06K9/2018 , G06K9/2027 , G06K9/2054 , H04N13/128 , H04N13/271 , H04N13/366
摘要： Methods and systems for face detection and tracking using an image-based capture device are disclosed herein. The method includes generating a depth image of a scene, generating a mask image from the depth image, and detecting a position of a face of a user in the scene using the mask image. The method also includes determining an intensity of the face using a first color channel of the mask image and adjusting a gain level of a first color channel of the image-based capture device directed at the scene to achieve a target intensity of the face.
摘要翻译： 本文公开了使用基于图像的捕获装置的面部检测和跟踪的方法和系统。 该方法包括生成场景的深度图像，从深度图像生成掩模图像，以及使用掩模图像来检测场景中的用户的脸部的位置。 该方法还包括使用掩模图像的第一颜色通道来确定面部的强度，并且调整指向场景的基于图像的捕获装置的第一颜色通道的增益水平以实现面部的目标强度。
-
公开(公告)号：US20130113956A1
公开(公告)日：2013-05-09
申请号：US13288964
申请日：2011-11-04
IPC分类号： H04N9/73
CPC分类号： H04N9/735 , G06F3/011 , G06F3/017 , G06K9/00201 , G06K9/00234 , G06K9/2018 , G06K9/2027 , G06K9/2054 , H04N13/128 , H04N13/271 , H04N13/366
摘要： Methods and systems for face detection and tracking using an image-based capture device are disclosed herein. The method includes generating a depth image of a scene, generating a mask image from the depth image, and detecting a position of a face of a user in the scene using the mask image. The method also includes determining an intensity of the face using a first color channel of the mask image and adjusting a gain level of a first color channel of the image-based capture device directed at the scene to achieve a target intensity of the face.
摘要翻译： 本文公开了使用基于图像的捕获装置的面部检测和跟踪的方法和系统。 该方法包括生成场景的深度图像，从深度图像生成掩模图像，以及使用掩模图像来检测场景中的用户的脸部的位置。 该方法还包括使用掩模图像的第一颜色通道来确定面部的强度，并且调整指向场景的基于图像的捕获装置的第一颜色通道的增益水平以实现面部的目标强度。
-
-
-
搜索结果
4 条记录 (耗时 0.026 秒)
