公开(公告)号：US20170186226A1

公开(公告)日：2017-06-29

申请号：US14982568

申请日：2015-12-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Thomas Joseph CASHMAN ,  David Joseph New TAN ,  Jamie Daniel Joseph SHOTTON ,  Andrew William FITZGIBBON ,  Sameh KHAMIS ,  Jonathan James TAYLOR ,  Toby SHARP ,  Daniel Stefan TARLOW

IPC: G06T17/20

CPC classification number: G06T17/20 ,  G06T7/251 ,  G06T2200/04 ,  G06T2207/30168 ,  G06T2207/30196

Abstract: Examples describe an apparatus for calibrating a three dimensional (3D) mesh model of an articulated object. The articulated object is an instance of a specified object class. The apparatus comprises an input configured to receive captured sensor data depicting the object. The apparatus has a calibration engine configured to compute values of shape parameters of the 3D mesh model which indicate which member of the object class is depicted in the captured sensor data, in order to calibrate the 3D mesh model. The calibration engine is configured to compute the values of the shape parameters with an optimization process to find at least one potential local or global minimum of an energy function, the energy function expressing a degree of similarity between data rendered from the model and the received sensor data.

公开(公告)号：US20230281863A1

公开(公告)日：2023-09-07

申请号：US17852175

申请日：2022-06-28

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Julien Pascal Christophe VALENTIN ,  Erroll William WOOD ,  Thomas Joseph CASHMAN ,  Martin de LA GORCE ,  Tadas BALTRUSAITIS ,  Daniel Stephen WILDE ,  Jingjing SHEN ,  Matthew Alastair JOHNSON ,  Charles Thomas HEWITT ,  Nikola MILOSAVLJEVIC ,  Stephan Joachim GARBIN ,  Toby SHARP ,  Ivan STOJILJKOVIC

IPC: G06T7/73 ,  G06T7/33 ,  G06T17/00 ,  G06T19/20

CPC classification number: G06T7/73 ,  G06T7/344 ,  G06T17/00 ,  G06T19/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2219/2004 ,  G06T2207/30201

Abstract: Keypoints are predicted in an image. Predictions are generated for each of the keypoints of an image as a 2D random variable, normally distributed with location (x, y) and standard deviation sigma. A neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. The trained neural network is used to predict keypoints of an image without generating a heatmap.

公开(公告)号：US20170186165A1

公开(公告)日：2017-06-29

申请号：US14982878

申请日：2015-12-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jonathan James TAYLOR ,  Thomas Joseph CASHMAN ,  Andrew William FITZGIBBON ,  Toby SHARP ,  Jamie Daniel Joseph SHOTTON

IPC: G06T7/00 ,  G06T7/20 ,  G06T17/20

CPC classification number: G06T17/205 ,  G06T7/251 ,  G06T7/75 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/30196

Abstract: A tracker is described which comprises an input configured to receive captured sensor data depicting an object. The tracker has a processor configured to access a rigged, smooth-surface model of the object and to compute values of pose parameters of the model by calculating an optimization to fit the model to data related to the captured sensor data. Variables representing correspondences between the data and the model are included in the optimization jointly with the pose parameters.

公开(公告)号：US20230316552A1

公开(公告)日：2023-10-05

申请号：US17713038

申请日：2022-04-04

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： JingJing SHEN ,  Erroll William WOOD ,  Toby SHARP ,  Ivan RAZUMENIC ,  Tadas BALTRUSAITIS ,  Julien Pascal Christophe VALENTIN ,  Predrag JOVANOVIC

IPC: G06T7/55 ,  H04N5/225 ,  G06V10/82 ,  G06T7/70 ,  G06T7/20 ,  G06T19/20 ,  G06V10/22 ,  G06V20/64 ,  G06T17/00 ,  G01S17/894 ,  G01S17/86

CPC classification number: G06T7/55 ,  H04N5/2258 ,  G06V10/82 ,  G06T7/70 ,  G06T7/20 ,  G06T19/20 ,  G06V10/22 ,  G06V20/647 ,  G06T17/00 ,  G01S17/894 ,  G01S17/86 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10021 ,  G06T2219/2016 ,  G06T2219/2004 ,  G06T2210/56 ,  G06T2200/08

Abstract: The techniques described herein disclose a system that is configured to detect and track the three-dimensional pose of an object (e.g., a head-mounted display device) in a color image using an accessible three-dimensional model of the object. The system uses the three-dimensional pose of the object to repair pixel depth values associated with a region (e.g., a surface) of the object that is composed of material that absorbs light emitted by a time-of-flight depth sensor to determine depth. Consequently, a color-depth image (e.g., a Red-Green-Blue-Depth image or RGB-D image) can be produced that does not include dark holes on and around the region of the object that is composed of material that absorbs light emitted by the time-of-flight depth sensor.

公开(公告)号：US20170372126A1

公开(公告)日：2017-12-28

申请号：US15701170

申请日：2017-09-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jamie Daniel Joseph SHOTTON ,  Cem KESKIN ,  Christoph RHEMANN ,  Toby SHARP ,  Duncan Paul ROBERTSON ,  Pushmeet KOHLI ,  Andrew William FITZGIBBON ,  Shahram IZADI

IPC: G06K9/00 ,  G01S7/48 ,  G01S7/491 ,  G01S17/10 ,  G06T7/50 ,  G01S17/89 ,  G01S17/36 ,  G06T7/11 ,  G06K9/62

CPC classification number: G06K9/00201 ,  G01S7/4808 ,  G01S7/4911 ,  G01S17/10 ,  G01S17/36 ,  G01S17/89 ,  G06K9/00362 ,  G06K9/00671 ,  G06K9/6282 ,  G06T7/11 ,  G06T7/50 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/10152 ,  G06T2207/20081

Abstract: Region of interest detection in raw time of flight images is described. For example, a computing device receives at least one raw image captured for a single frame by a time of flight camera. The raw image depicts one or more objects in an environment of the time of flight camera (such as human hands, bodies or any other objects). The raw image is input to a trained region detector and in response one or more regions of interest in the raw image are received. A received region of interest comprises image elements of the raw image which are predicted to depict at least part of one of the objects. A depth computation logic computes depth from the one or more regions of interest of the raw image.