公开(公告)号：US09380224B2

公开(公告)日：2016-06-28

申请号：US14193686

申请日：2014-02-28

Applicant: Microsoft Corporation

Inventor： Cem Keskin ,  Sean Ryan Francesco Fanello ,  Shahram Izadi ,  Pushmeet Kohli ,  David Kim ,  David Sweeney ,  Jamie Daniel Joseph Shotton ,  Duncan Paul Robertson ,  Sing Bing Kang

IPC: G06K9/00 ,  H04N5/33 ,  G06T7/00 ,  G06K9/20 ,  G06K9/62

CPC classification number: H04N5/33 ,  G06K9/00201 ,  G06K9/2018 ,  G06K9/6219 ,  G06K9/6282 ,  G06T7/521 ,  G06T2200/04 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20081 ,  G06T2207/30201

Abstract: A method of sensing depth using an infrared camera. In an example method, an infrared image of a scene is received from an infrared camera. The infrared image is applied to a trained machine learning component which uses the intensity of image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the infrared camera. In various examples, the machine line component comprises one or more random decision forests.

Abstract translation: 使用红外摄像机感测深度的方法。 在一个示例方法中，从红外相机接收场景的红外图像。 将红外图像应用于训练有素的机器学习部件，其使用图像元素的强度来分配全部或部分图像元素，该深度值表示由图像元素描绘的表面与红外相机之间的距离。 在各种示例中，机器线路部件包括一个或多个随机决策树。

公开(公告)号：US20150248764A1

公开(公告)日：2015-09-03

申请号：US14193686

申请日：2014-02-28

Applicant: Microsoft Corporation

Inventor： Cem Keskin ,  Sean Ryan Francesco Fanello ,  Shahram Izadi ,  Pushmeet Kohli ,  David Kim ,  David Sweeney ,  Jamie Daniel Joesph Shotton ,  Duncan Paul Robertson ,  Sing Bing Kang

IPC: G06T7/00 ,  H04N5/33

CPC classification number: H04N5/33 ,  G06K9/00201 ,  G06K9/2018 ,  G06K9/6219 ,  G06K9/6282 ,  G06T7/521 ,  G06T2200/04 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20081 ,  G06T2207/30201

Abstract: A method of sensing depth using an infrared camera. In an example method, an infrared image of a scene is received from an infrared camera. The infrared image is applied to a trained machine learning component which uses the intensity of image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the infrared camera. In various examples, the machine line component comprises one or more random decision forests.

Abstract translation: 使用红外摄像机感测深度的方法。 在一个示例方法中，从红外相机接收场景的红外图像。 将红外图像应用于训练有素的机器学习部件，其使用图像元素的强度来分配全部或部分图像元素，该深度值表示由图像元素描绘的表面与红外相机之间的距离。 在各种示例中，机器线路部件包括一个或多个随机决策树。