公开(公告)号：US20200186783A1

公开(公告)日：2020-06-11

申请号：US16704058

申请日：2019-12-05

Applicant: Intel Corporation

Inventor： Daniel C. Middleton ,  Jianbo Shi

IPC: H04N13/271 ,  G06T5/00 ,  G06T3/00 ,  G06T7/50 ,  G06T15/20 ,  H04N13/111

Abstract: Techniques are provided for synthesis of transformed image views, based on a reference image, using depth information. The transformed image views may simulate a change in position or focal length of a camera that produced the reference image. An example system includes an image transformation circuit configured to transform the reference image corresponding to a first viewpoint, to a transformed image corresponding to a second viewpoint. The system also includes an inverse warping circuit configured to calculate a mapping from the pixels of the transformed image to corresponding pixels of the reference image. The system further includes a hole detection circuit configured to detect holes in the transformed image based on depth discontinuities between the reference and transformed images; and a hole filling circuit configured to in-fill the detected holes using a sampling of selected neighboring pixels from the reference image, to synthesize a view based on the transformed image.

公开(公告)号：US09503709B2

公开(公告)日：2016-11-22

申请号：US14140929

申请日：2013-12-26

Applicant: INTEL CORPORATION

Inventor： Jianbo Shi ,  Daniel C. Middleton

IPC: H04N13/02

CPC classification number: H04N13/282 ,  H04N13/243

Abstract: Devices, systems and methods employing modular camera arrays are described. A two-dimensional array of cameras may be arranged in a non-rectangular array. A first camera, a second camera, and a third camera in the array may be located approximately equidistant from each other, and/or may be arranged approximately in an equilateral triangle, an isosceles triangle, a scalene triangle, and/or a right triangle.

Abstract translation: 描述了使用模块化摄像机阵列的设备，系统和方法。 相机的二维阵列可以以非矩形阵列排列。 阵列中的第一相机，第二相机和第三相机可以彼此大致等距定位，和/或可以大致布置在等边三角形，等腰三角形，斜角三角形和/或直角三角形 。

公开(公告)号：US11153553B2

公开(公告)日：2021-10-19

申请号：US16704058

申请日：2019-12-05

Applicant: Intel Corporation

Inventor： Daniel C. Middleton ,  Jianbo Shi

IPC: G06K9/32 ,  H04N13/271 ,  G06T3/00 ,  G06T5/00 ,  H04N13/111 ,  G06T15/20 ,  G06T7/50

Abstract: Techniques are provided for synthesis of transformed image views, based on a reference image, using depth information. The transformed image views may simulate a change in position or focal length of a camera that produced the reference image. An example system includes an image transformation circuit configured to transform the reference image corresponding to a first viewpoint, to a transformed image corresponding to a second viewpoint. The system also includes an inverse warping circuit configured to calculate a mapping from the pixels of the transformed image to corresponding pixels of the reference image. The system further includes a hole detection circuit configured to detect holes in the transformed image based on depth discontinuities between the reference and transformed images; and a hole filling circuit configured to in-fill the detected holes using a sampling of selected neighboring pixels from the reference image, to synthesize a view based on the transformed image.

公开(公告)号：US09596459B2

公开(公告)日：2017-03-14

申请号：US14498793

申请日：2014-09-26

Applicant: INTEL CORPORATION

Inventor： Todd Keaffaber ,  Daniel Middleton ,  Gilson Goncalves de Lima ,  Martin Meloun ,  Varun Nasery ,  Jianbo Shi ,  Kabeer Manchanda ,  Philip Kim ,  Christopher Bernard ,  Yedong Niu

IPC: H04N9/47 ,  H04N9/80 ,  H04N17/00 ,  G06T7/00 ,  H04N5/225

CPC classification number: H04N17/002 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/30208 ,  H04N5/2258 ,  H04N5/247

Abstract: Techniques for calibration of image capturing devices are described herein. The techniques include capturing one or more images at a first target, capturing one or more images at a second target, capturing one or more images at a third target, capturing one or more images at a fourth target, and calibrating a multi-camera system based on the captured images.

Abstract translation: 本文描述了图像捕获装置的校准技术。 所述技术包括在第一目标处捕获一个或多个图像，在第二目标处捕获一个或多个图像，在第三目标处捕获一个或多个图像，在第四目标处捕获一个或多个图像，以及校准多相机系统 基于捕获的图像。

公开(公告)号：US10567739B2

公开(公告)日：2020-02-18

申请号：US15136501

申请日：2016-04-22

Applicant: INTEL CORPORATION

Inventor： Daniel C. Middleton ,  Jianbo Shi

IPC: G06K9/32 ,  H04N13/271 ,  G06T3/00 ,  G06T5/00

Abstract: Techniques are provided for synthesis of transformed image views, based on a reference image, using depth information. The transformed image views may simulate a change in position or focal length of a camera that produced the reference image. An example system includes an image transformation circuit configured to transform the reference image corresponding to a first viewpoint, to a transformed image corresponding to a second viewpoint. The system also includes an inverse warping circuit configured to calculate a mapping from the pixels of the transformed image to corresponding pixels of the reference image. The system further includes a hole detection circuit configured to detect holes in the transformed image based on depth discontinuities between the reference and transformed images; and a hole filling circuit configured to in-fill the detected holes using a sampling of selected neighboring pixels from the reference image, to synthesize a view based on the transformed image.

公开(公告)号：US20170308990A1

公开(公告)日：2017-10-26

申请号：US15136501

申请日：2016-04-22

Applicant: INTEL CORPORATION

Inventor： Daniel C. Middleton ,  Jianbo Shi

IPC: G06T3/00 ,  G06T5/00 ,  G06T3/40 ,  H04N13/02

CPC classification number: H04N13/271 ,  G06T3/0093 ,  G06T5/005 ,  G06T7/50 ,  G06T15/20 ,  G06T2207/10028 ,  H04N13/111

Abstract: Techniques are provided for synthesis of transformed image views, based on a reference image, using depth information. The transformed image views may simulate a change in position or focal length of a camera that produced the reference image. An example system includes an image transformation circuit configured to transform the reference image corresponding to a first viewpoint, to a transformed image corresponding to a second viewpoint. The system also includes an inverse warping circuit configured to calculate a mapping from the pixels of the transformed image to corresponding pixels of the reference image. The system further includes a hole detection circuit configured to detect holes in the transformed image based on depth discontinuities between the reference and transformed images; and a hole filling circuit configured to in-fill the detected holes using a sampling of selected neighboring pixels from the reference image, to synthesize a view based on the transformed image.