公开(公告)号：WO2017095576A1

公开(公告)日：2017-06-08

申请号：PCT/US2016/059965

申请日：2016-11-01

Applicant: INTEL CORPORATION

Inventor： RYU, Wooju ,  KIM, Tae-Hoon ,  PARK, Minje ,  YOON, Boogeon ,  LEE, Jinwook

IPC: G06T3/00 ,  G06T7/00 ,  G06T15/00

CPC classification number: G06K9/00208 ,  G06K9/00214 ,  G06K9/4604 ,  G06K9/4676 ,  G06K9/481 ,  G06K9/6211 ,  G06T7/0061 ,  G06T7/149

Abstract: A system, article, and method of curved object recognition using image matching for image processing, comprising: using paired 2D-3D point(s) to form a perspective projection function to determine a geometric correspondence between target object and reference object(s) and that converts the 2D points into 3D points at the target object.

Abstract translation: 一种使用图像匹配进行图像处理的弯曲物体识别的系统，物品和方法，包括：使用成对的2D-3D点形成透视投影函数以确定目标之间的几何对应关系 对象和参考对象，并将2D点转换为目标对象的3D点。

公开(公告)号：WO2017095510A1

公开(公告)日：2017-06-08

申请号：PCT/US2016/053672

申请日：2016-09-26

Applicant: INTEL CORPORATION

Inventor： KIM, Tae-Hoon

IPC: G06F15/16 ,  G06K9/46 ,  G06K9/62 ,  G06F17/30

CPC classification number: G06K9/66 ,  G06F17/30256 ,  G06K9/00624 ,  G06K9/00664 ,  G06K2209/21 ,  H04L67/32

Abstract: Attributes of large scale computer vision systems may be made available to users of more limited processer-based systems by dynamically and adaptively updating recognizers into a smaller scale device from a connected larger scale device, based on the user's situational context and behavior. A recognizer is a hardware, software or firmware module specialized to use computer vision to recognize a defined class of imaged objects.

Abstract translation: 大规模计算机视觉系统的属性可以通过基于用户的动态和适应性地将识别器更新为来自连接的较大规模设备的较小规模设备而提供给更受限制的基于处理器的系统的用户 情境背景和行为。 识别器是一个硬件，软件或固件模块，专门用于使用计算机视觉识别定义的一类成像对象。

公开(公告)号：WO2016073105A1

公开(公告)日：2016-05-12

申请号：PCT/US2015/054065

申请日：2015-10-05

Applicant: INTEL CORPORATION

Inventor： PARK, Minje ,  LEE, Hyungsoo ,  JE, Hongmo ,  KIM, Tae-Hoon ,  CHEON, Yeongjae ,  KIM, Taesup

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/3275 ,  G06K9/00248

Abstract: Computer-readable storage media, computing devices and methods are discussed herein. In embodiments, a computing device may be configured to perform facial recognition based on gradient based feature extractions of images of faces. In embodiments, the computing device may be configured to determine directional matching patterns of the images from the gradient based feature extraction and may utilize these directional matching patterns in performing a facial recognition analysis of the images of faces. Other embodiments may be described and/or claimed.

Abstract translation: 本文讨论了计算机可读存储介质，计算设备和方法。 在实施例中，计算设备可以被配置为基于面部图像的基于梯度的特征提取来执行面部识别。 在实施例中，计算设备可以被配置为从基于梯度的特征提取来确定图像的方向匹配模式，并且可以在对面部图像执行面部识别分析时利用这些方向匹配模式。 可以描述和/或要求保护其他实施例。

公开(公告)号：WO2017101094A1

公开(公告)日：2017-06-22

申请号：PCT/CN2015/097826

申请日：2015-12-18

Applicant: INTEL CORPORATION ,  PARK, Minje ,  KIM, Tae-Hoon ,  JU, Myung-Ho ,  YI, Jihyeon ,  SHEN, Xiaolu ,  ZHANG, Lidan ,  LI, Qiang

Inventor： PARK, Minje ,  KIM, Tae-Hoon ,  JU, Myung-Ho ,  YI, Jihyeon ,  SHEN, Xiaolu ,  ZHANG, Lidan ,  LI, Qiang

IPC: G06T13/40

CPC classification number: G06T13/40 ,  G06T7/73 ,  G06T17/20 ,  G06T2207/20084 ,  G06T2207/30201 ,  G06T2210/44

Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. The real-time provision of high quality avatar animation is enabled, at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.

Abstract translation: 这里公开的头像动画系统提供基于人脸的变化的人脸的高质量实时头像动画。 高质量化身动画的实时提供至少部分地由多帧回归器实现，该多帧回归器配置成将描述两幅或多幅图像中描绘的面部表情的信息映射到描述单个化身混合形状的信息。 该两个或更多个图像可以是时间上连续的图像。 该多帧回归器实现机器学习组件，其从描述主体的脸部的信息和/或描述先前由多帧回归器生成的化身动画帧的信息来生成高质量化身动画。 机器学习组件可以使用一组描述人类面部表情的训练图像和由专业动画师创作的化身动画来反映在该组训练图像中描绘的面部表情。

公开(公告)号：WO2018063523A1

公开(公告)日：2018-04-05

申请号：PCT/US2017/046310

申请日：2017-08-10

Applicant: INTEL CORPORATION

Inventor： BURNS, Geoffrey F. ,  SUKUMAR, Vinesh ,  KIM, Tae-Hoon

IPC: H04N5/14 ,  H04N5/20 ,  G06T7/20

CPC classification number: H04N19/51 ,  G06T7/20 ,  G06T2207/10024 ,  G06T2207/20021 ,  H04N19/117 ,  H04N19/54

Abstract: Techniques are provided for motion estimation using hybrid video imaging based on frame-based capture and event-based capture. A methodology implementing the techniques according to an embodiment includes receiving a sequence of pixel events, generated asynchronously by an event-based video camera, and receiving a sequence of image frames generated by a frame-based video camera at a frame sampling period. The method also includes integrating a subset of the sequence of pixel events, occurring within the frame sampling period between two of the image frames, to generate a pixel motion vector representing motion of the pixel between the two image frames. The method further includes mapping the pixel motion vector to a tile of one of the image frames to generate an estimated motion vector associated with that tile.

Abstract translation: 提供了基于基于帧的捕捉和基于事件的捕捉的使用混合视频成像的运动估计技术。 实施根据实施例的技术的方法包括接收由基于事件的摄像机异步生成的像素事件序列，并且在帧采样周期接收由基于帧的摄像机生成的图像帧序列。 该方法还包括对在两个图像帧之间的帧采样周期内出现的像素事件序列的子集进行积分，以生成表示像素在两个图像帧之间的运动的像素运动向量。 该方法进一步包括将像素运动向量映射到图像帧之一的瓦片以产生与该瓦片相关联的估计运动向量。

公开(公告)号：WO2016094002A1

公开(公告)日：2016-06-16

申请号：PCT/US2015/059736

申请日：2015-11-09

Applicant: INTEL CORPORATION

Inventor： LEE, Jinwook ,  JUN, Bongjin ,  KIM, Tae-Hoon

IPC: G06K9/00 ,  G06F21/32

CPC classification number: G06K9/00275 ,  G06K9/00228 ,  G06K9/00281 ,  G06K9/00973 ,  G06K9/68 ,  G06T2207/10004 ,  G06T2207/30201

Abstract: Apparatuses, methods and storage medium associated with face detection are disclosed. In embodiments, an apparatus may comprise one or more processors, cache memory, a lookup table of feature patterns, and a face detector. The lookup table is to be loaded into the cache memory, during operation, for use to detect whether a face is present in an image. The feature patterns within the lookup table are organized within the lookup table in accordance with relative connectivity of the feature patterns. The face detector to detect whether a face is present in an image, may use the lookup table of feature patterns loaded into the cache memory during detection for the face. Other embodiments may be described and/or claimed.

Abstract translation: 公开了与面部检测相关联的装置，方法和存储介质。 在实施例中，装置可以包括一个或多个处理器，高速缓冲存储器，特征图案的查找表和面部检测器。 在操作期间，查找表将被加载到高速缓冲存储器中，以用于检测图像中是否存在面部。 根据特征图案的相对连接性，查找表内的特征图案被组织在查找表内。 用于检测脸部是否存在于图像中的脸部检测器可以在检测脸部期间使用加载到高速缓冲存储器中的特征图案的查找表。 可以描述和/或要求保护其他实施例。

公开(公告)号：WO2015192369A1

公开(公告)日：2015-12-23

申请号：PCT/CN2014/080382

申请日：2014-06-20

Applicant: INTEL CORPORATION ,  PARK, Minje ,  DUCHENNE, Olivier ,  CHEON, Yeongjae ,  KIM, Tae-Hoon ,  SHEN, Xiaolu ,  DU, Yangzhou ,  RYU, Wooju ,  JU, Myung-Ho

Inventor： PARK, Minje ,  DUCHENNE, Olivier ,  CHEON, Yeongjae ,  KIM, Tae-Hoon ,  SHEN, Xiaolu ,  DU, Yangzhou ,  RYU, Wooju ,  JU, Myung-Ho

IPC: G06T15/08

CPC classification number: G06T17/205 ,  G06K9/00208 ,  G06K9/00214 ,  G06K9/00221 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06T7/251 ,  G06T17/20 ,  G06T2200/04 ,  G06T2207/30201

Abstract: Apparatuses, methods and storage medium associated with 3D face model reconstruction are disclosed herein. In embodiments, an apparatus may include a facial landmark detector, a model fitter and a model tracker. The facial landmark detector may be configured to detect a plurality of landmarks of a face and their locations within each of a plurality of image frames. The model fitter may be configured to generate a 3D model of the face from a 3D model of a neutral face, in view of detected landmarks of the face and their locations within a first one of the plurality of image frames. The model tracker may be configured to maintain the 3D model to track the face in subsequent image frames, successively updating the 3D model in view of detected landmarks of the face and their locations within each of successive ones of the plurality of image frames. In embodiments, the facial landmark detector may include a face detector, an initial facial landmark detector, and one or more facial landmark detection linear regressors. Other embodiments may be described and/or claimed.

Abstract translation: 本文公开了与3D脸部模型重建相关联的装置，方法和存储介质。 在实施例中，装置可以包括面部地标检测器，模型装配器和模型跟踪器。 面部地标检测器可以被配置为检测面部的多个界标及其在多个图像帧的每一个内的位置。 考虑到检测到的面部的标记及其在多个图像帧的第一个图像帧中的位置，模型拟合器可以被配置为从中立面的3D模型生成面部的3D模型。 模型跟踪器可以被配置为维持3D模型以跟踪后续图像帧中的面部，从而考虑到检测到的面部的界标及其在多个图像帧中的每个连续图像帧中的位置之间的连续更新3D模型。 在实施例中，面部地标检测器可以包括面部检测器，初始面部地标检测器和一个或多个面部地标检测线性回归器。 可以描述和/或要求保护其他实施例。

公开(公告)号：WO2015139231A1

公开(公告)日：2015-09-24

申请号：PCT/CN2014/073695

申请日：2014-03-19

Applicant: INTEL CORPORATION ,  DU, Yangzhou ,  KIM, Tae-Hoon ,  LI, Wenlong ,  LI, Qiang ,  TONG, Xiaofeng ,  WANG, Tao ,  PARK, Minje ,  DUCHENNE, Olivier ,  ZHANG, Yimin ,  CHEON, Yeongjae ,  JUN, Bongjin ,  RYU, Wooju ,  SACHSON, Thomas ,  SMILEY, Mary D.

Inventor： DU, Yangzhou ,  KIM, Tae-Hoon ,  LI, Wenlong ,  LI, Qiang ,  TONG, Xiaofeng ,  WANG, Tao ,  PARK, Minje ,  DUCHENNE, Olivier ,  ZHANG, Yimin ,  CHEON, Yeongjae ,  JUN, Bongjin ,  RYU, Wooju ,  SACHSON, Thomas ,  SMILEY, Mary D.

IPC: G06T13/40

CPC classification number: G06T13/40 ,  G06K9/00308 ,  G06K9/00315 ,  G06K9/00335 ,  G06K2009/4666 ,  G06T7/251 ,  G06T15/005 ,  G06T2200/04 ,  G06T2207/10016 ,  G06T2207/30201

Abstract: Apparatuses, methods and storage medium associated with animating and rendering an avatar are disclosed herein. In embodiments, an apparatus may include a facial mesh tracker to receive a plurality of image frames, detect facial action movements of a face and head pose gestures of a head within the plurality of image frames, and output a plurality of facial motion parameters and head pose parameters that depict facial action movements and head pose gestures detected, all in real time, for animation and rendering of an avatar. The facial action movements and head pose gestures may be detected through inter-frame differences for a mouth and an eye, or the head, based on pixel sampling of the image frames. The facial action movements may include opening or closing of a mouth, and blinking of an eye. The head pose gestures may include head rotation such as pitch, yaw, roll, and head movement along horizontal and vertical direction, and the head comes closer or goes farther from the camera. Other embodiments may be described and/or claimed.

Abstract translation: 本文公开了与动画和呈现化身相关联的装置，方法和存储介质。 在实施例中，装置可以包括面部网格跟踪器，用于接收多个图像帧，检测多个图像帧内的头部的脸部和头部姿势手势的面部动作运动，并且输出多个面部运动参数和头部 构成参数，其描绘了所有实时检测到的面部动作动作和头部姿势手势，用于动画和呈现头像。 基于图像帧的像素采样，可以通过口和眼或头部的帧间差异来检测面部动作运动和头部姿势手势。 面部动作动作可以包括开口或闭合嘴，以及眼睛的眨眼。 头部姿势手势可以包括水平和垂直方向的头部旋转，例如俯仰，偏航，滚动和头部移动，并且头部靠近或离开相机更远。 可以描述和/或要求保护其他实施例。

公开(公告)号：WO2019108170A1

公开(公告)日：2019-06-06

申请号：PCT/US2017/063585

申请日：2017-11-29

Applicant: INTEL CORPORATION

Inventor： KIM, Tae-Hoon ,  PARK, Minje

IPC: G06T3/40 ,  G06T7/11 ,  G06N3/08

Abstract: Methods and apparatus to convert images for computer-vision systems are disclosed. An example computer-vision system includes an image converter (112) to convert a near infrared light first image (202) to form a visible light image (206), and to update a coefficient of the image converter (112) based on a difference (214), an object recognizer (102) to recognize an object (208) in the first visible light image (206), and an object recognition analyzer (210) to determine the difference (214) between the object (208) recognized in the first visible light image (206) and an object (212) associated with the near infrared light image (202).

公开(公告)号：WO2016077010A1

公开(公告)日：2016-05-19

申请号：PCT/US2015/055371

申请日：2015-10-13

Applicant: INTEL CORPORATION

Inventor： LEE, Jinwook ,  PARK, Yongchan ,  JE, Hongmo ,  KIM, Tae-Hoon

IPC: H04N13/00 ,  H04N13/02 ,  H04N5/225

CPC classification number: G06K9/00711 ,  G06K9/4642 ,  G06K9/4652 ,  G06T7/246

Abstract: System, apparatus, method, and computer readable media for on-the-fly captured image data object tracking. An image or video stream is processed to detect and track an object in concurrence with generation of the stream by a camera module. In one exemplary embodiment, HD image frames are processed at a rate of 30 fps, or more, to track one or more target object. In embodiments, object detection is validated prior to employing detected object descriptor(s) as learning data to generate or update an object model. A device platform including a camera module and comporting with the exemplary architecture may provide 3A functions based on objects robustly tracked in accordance with embodiments.

Abstract translation: 系统，装置，方法和计算机可读介质，用于即时拍摄的图像数据对象跟踪。 处理图像或视频流以通过相机模块生成流来检测和跟踪对象。 在一个示例性实施例中，以30fps或更大的速率处理高清图像帧以跟踪一个或多个目标对象。 在实施例中，在使用检测到的对象描述符作为学习数据来生成或更新对象模型之前，对对象检测进行验证。 包括相机模块和与示例性体系结构对比的设备平台可以基于根据实施例坚固跟踪的对象提供3A功能。