公开(公告)号：US20190098281A1

公开(公告)日：2019-03-28

申请号：US16072231

申请日：2016-02-25

Applicant: Yi WU ,  Yong JIANG ,  INTEL CORPORATION

Inventor： YI WU ,  YONG JIANG

IPC: H04N13/128 ,  H04N13/144 ,  G06T7/246 ,  G06T7/90 ,  G06K9/62 ,  G06T7/73 ,  G06T7/593 ,  H04N13/239

CPC classification number: H04N13/128 ,  G06K9/6215 ,  G06T7/223 ,  G06T7/248 ,  G06T7/593 ,  G06T7/74 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/10024 ,  H04N13/144 ,  H04N13/239 ,  H04N2013/0081 ,  H04N2013/0085

Abstract: Techniques are provided for calculating temporally coherent disparity values for pixels in a sequence of image frames. An example method may include calculating initial spatial disparity costs between a pixel of a first image frame from a reference camera and pixels from an image frame from a secondary camera. The method may also include estimating a motion vector for the pixel of the first reference camera image frame to a corresponding pixel from a second reference camera image frame. The method may further include calculating a confidence value for the estimated motion vector based on a measure of similarity between the colors of the pixels of the first and second image frames from the reference camera. The method may further include calculating temporally coherent disparity costs based on the initial spatial disparity costs weighted by the confidence value and selecting a disparity value based on those costs.

公开(公告)号：US20150271473A1

公开(公告)日：2015-09-24

申请号：US14630469

申请日：2015-02-24

Applicant: Intel Corporation

Inventor： TAO MA ,  YI WU ,  OSCAR NESTARES ,  KALPANA SESHADRINATHAN ,  WEI SUN

IPC: H04N13/02 ,  G06T7/00 ,  G06T5/00 ,  H04N5/247

CPC classification number: H04N13/243 ,  G06K9/3233 ,  G06T5/006 ,  G06T7/97 ,  G06T2207/10012 ,  G06T2207/20228 ,  H04N5/247 ,  H04N2013/0081

Abstract: Techniques for improved image disparity estimation are described. In one embodiment, for example, an apparatus may comprise a processor circuit and an imaging management module, and the imaging management module may be operable by the processor circuit to determine a measured horizontal disparity factor and a measured vertical disparity factor for a rectified image array, determine a composite horizontal disparity factor for the rectified image array based on the measured horizontal disparity factor and an implied horizontal disparity factor, and determine a composite vertical disparity factor for the rectified image array based on the measured vertical disparity factor and an implied vertical disparity factor. Other embodiments are described and claimed.

Abstract translation: 描述了用于改进图像差异估计的技术。 在一个实施例中，例如，装置可以包括处理器电路和成像管理模块，并且成像管理模块可以由处理器电路操作以确定经校正的图像阵列的测量的水平视差因子和测量的垂直视差因子 基于测量的水平视差因子和隐含的水平视差因子确定整流图像阵列的复合水平视差系数，并根据测量的垂直视差因子和隐含的垂直视差确定整流图像阵列的复合垂直视差系数 因子。 描述和要求保护其他实施例。

公开(公告)号：US20160165216A1

公开(公告)日：2016-06-09

申请号：US14565149

申请日：2014-12-09

Applicant: INTEL CORPORATION

Inventor： YI WU ,  JIANG YONG

IPC: H04N13/02 ,  H04N5/357 ,  G06T7/00 ,  H04N5/369 ,  G06T5/00 ,  G06F3/041 ,  H04N13/00 ,  H04N5/225 ,  G06T5/40

CPC classification number: H04N13/271 ,  G06T7/97 ,  H04N5/2258 ,  H04N5/247 ,  H04N5/3572 ,  H04N5/3696 ,  H04N13/15 ,  H04N13/243 ,  H04N13/257 ,  H04N13/282 ,  H04N2013/0077 ,  H04N2013/0081 ,  H04N2013/0092 ,  H04N2101/00

Abstract: A range is determined for a disparity search for images from an image sensor array. In one example, a method includes receiving a reference image and a second image of a scene from multiple cameras of a camera array, detecting feature points of the reference image, matching points of the detected features to points of the second image, determining a maximum disparity between the reference image and the second image, and determining disparities between the reference image and the second image by comparing points of the reference image to points of the second image wherein the points of the second image are limited to points within the maximum disparity.

Abstract translation: 对于来自图像传感器阵列的图像的视差搜索确定范围。 在一个示例中，一种方法包括从摄像机阵列的多个摄像机接收场景的参考图像和第二图像，检测参考图像的特征点，检测到的特征的匹配点与第二图像的点，确定最大值 参考图像和第二图像之间的差异，以及通过将参考图像的点与第二图像的点相比较来确定参考图像和第二图像之间的差异，其中第二图像的点被限制在最大视差内的点。

公开(公告)号：US20160127616A1

公开(公告)日：2016-05-05

申请号：US14529948

申请日：2014-10-31

Applicant: Intel Corporation

Inventor： KALPANA SESHADRINATHAN ,  YI WU

IPC: H04N5/217 ,  G06T5/40 ,  G06T5/50

CPC classification number: G06T5/40 ,  G06T5/007 ,  G06T5/50 ,  H04N5/23229 ,  H04N2013/0081

Abstract: Global matching of pixel data across multiple images. Pixel values of an input image are modified to better match a reference image with a slope thresholded histogram matching function. Visual artifacts are reduced by avoiding large pixel value modifications. For large intensity variations across the input and reference image, the slope of the mapping function is thresholded. Modification to the input image is therefore limited and a corresponding modification to the reference image is made to improve the image matching. More than two images may be matched by iteratively modifying a cumulative mass function of a reference image to accommodate thresholded modification of multiple input images. A device may include logic to match pixel values across a plurality of image frames generated from a plurality of image sensors on the device. Once matched, image frames may be reliably processed further for pixel correspondence, or otherwise.

Abstract translation: 跨多个图像的像素数据的全局匹配。 修改输入图像的像素值以使参考图像与斜率阈值直方图匹配函数更好地匹配。 通过避免大的像素值修改来减少视觉伪像。 对于输入和参考图像的大强度变化，映射函数的斜率被阈值化。 因此，对输入图像的修改被限制，并且对参考图像进行相应的修改以改善图像匹配。 通过迭代地修改参考图像的累积质量函数以适应多个输入图像的阈值修改，可以匹配两个以上的图像。 设备可以包括用于匹配从设备上的多个图像传感器生成的多个图像帧上的像素值的逻辑。 一旦匹配，图像帧可以进一步可靠地进行像素对应，或以其他方式。

公开(公告)号：US20160071279A1

公开(公告)日：2016-03-10

申请号：US14542040

申请日：2014-11-14

Applicant: INTEL CORPORATION

Inventor： YI WU ,  Jiang Yong

IPC: G06T7/00 ,  H04N13/00 ,  H04N13/02 ,  G06T3/40

CPC classification number: H04N13/243 ,  G06T3/40 ,  G06T7/97 ,  H04N13/128 ,  H04N13/271 ,  H04N2013/0081

Abstract: Disparity is determined for images from an array of disparate image sensors. In one example, a method includes processing images from multiple cameras of a camera array to reduce variations caused by variations in the in the image sensors of the respective cameras, the multiple cameras including a reference camera and at least one secondary camera, and determining multiple baseline disparities from the image from the reference camera to the images from the secondary cameras.

Abstract translation: 对于来自不同图像传感器阵列的图像确定视差。 在一个示例中，一种方法包括处理来自相机阵列的多个相机的图像，以减少由各个相机的图像传感器中的变化引起的变化，所述多个相机包括参考相机和至少一个次要相机，并且确定多个 从参考摄像机的图像到来自次要摄像机的图像的基线差异。