公开(公告)号：US09384551B2

公开(公告)日：2016-07-05

申请号：US13858813

申请日：2013-04-08

Applicant: Amazon Technologies, Inc.

Inventor： Sharadh Ramaswamy ,  Matthew Paul Bell ,  Dmitri Khoklov ,  David W. Stafford ,  Isaac Scott Noble

IPC: H04N13/02 ,  G06T7/00

CPC classification number: G06T7/002 ,  G06T7/85 ,  H04N13/239 ,  H04N13/243 ,  H04N2213/001

Abstract: An electronic device can have two or more pairs of cameras capable of performing three-dimensional imaging. In order to provide accurate disparity information, these cameras should be sufficiently rectified. Automatic rectification can be performed by periodically capturing images with the cameras of interest, and locating matching feature points in corresponding images captured by those cameras. Small misalignment errors can be treated as linear translations, such that a set of linear equations can be used to solve for the misalignments. Another process can process a set of homographies for the cameras until a cost function converges. Various other approaches can be used as well, such as to directly solve for yaw, pitch, and roll errors. Once this information is obtained, the misalignment values (or related values) can be stored for use in correcting images subsequently captured by those cameras.

Abstract translation: 电子设备可以具有能够执行三维成像的两对或更多对相机。 为了提供准确的视差信息，这些摄像机应该被充分纠正。 可以通过周围拍摄感兴趣的摄像机的图像，并将匹配的特征点定位在由这些摄像机拍摄的相应图像中，从而进行自动校正。 小的对准误差可以被视为线性平移，使得可以使用一组线性方程来解决不对准。 另一个过程可以处理一组相机的同画，直到成本函数收敛。 也可以使用各种其他方法，例如直接解决偏航，俯仰和滚动误差。 一旦得到该信息，就可以存储未对准值（或相关值），以用于校正随后由这些相机拍摄的图像。

公开(公告)号：US20140300704A1

公开(公告)日：2014-10-09

申请号：US13858813

申请日：2013-04-08

Applicant: Amazon Technologies, Inc.

Inventor： Sharadh Ramaswamy ,  Matthew Paul Bell ,  Dmitri Khoklov ,  David W. Stafford ,  Isaac Scott Noble

IPC: H04N13/02

CPC classification number: G06T7/002 ,  G06T7/85 ,  H04N13/239 ,  H04N13/243 ,  H04N2213/001

Abstract: An electronic device can have two or more pairs of cameras capable of performing three-dimensional imaging. In order to provide accurate disparity information, these cameras should be sufficiently rectified. Automatic rectification can be performed by periodically capturing images with the cameras of interest, and locating matching feature points in corresponding images captured by those cameras. Small misalignment errors can be treated as linear translations, such that a set of linear equations can be used to solve for the misalignments. Another process can process a set of homographies for the cameras until a cost function converges. Various other approaches can be used as well, such as to directly solve for yaw, pitch, and roll errors. Once this information is obtained, the misalignment values (or related values) can be stored for use in correcting images subsequently captured by those cameras.

Abstract translation: 电子设备可以具有能够执行三维成像的两对或更多对相机。 为了提供准确的视差信息，这些摄像机应该被充分纠正。 可以通过周围拍摄感兴趣的摄像机的图像，并将匹配的特征点定位在由这些摄像机拍摄的相应图像中，从而进行自动校正。 小的对准误差可以被视为线性平移，使得可以使用一组线性方程来解决不对准。 另一个过程可以处理一组相机的同画，直到成本函数收敛。 也可以使用各种其他方法，例如直接解决偏航，俯仰和滚动误差。 一旦得到该信息，就可以存储未对准值（或相关值），以用于校正随后由这些相机拍摄的图像。

公开(公告)号：US09602806B1

公开(公告)日：2017-03-21

申请号：US13914469

申请日：2013-06-10

Applicant: Amazon Technologies, Inc.

Inventor： David W. Stafford ,  Jennifer Silva ,  Edward Ackley Falk ,  Robert King Myers

IPC: H04N13/02 ,  H04N13/00 ,  H04N19/597 ,  G06T7/00 ,  H04N13/04

CPC classification number: H04N13/194 ,  G06T7/85 ,  G06T2207/10012 ,  H04N13/156 ,  H04N13/189 ,  H04N13/243 ,  H04N13/25 ,  H04N13/334 ,  H04N19/597

Abstract: Approaches discussed herein enable a computing device, such as a phone or tablet computer, to automatically recalibrate cameras used to capture three-dimensional images. A proximity sensor can be used to determine the distance to an object at approximately the time that three-dimensional image data is captured that includes a representation of the object. The apparent distance to the object, from the disparity of the three-dimensional image data, can be compared against the detected distance as measured by the proximity sensor. The difference between the detected and apparent distance, or the corresponding disparity values, can be used to determine a relative misalignment among the cameras, when then can be used to update the appropriate calibration parameters.

公开(公告)号：US09503703B1

公开(公告)日：2016-11-22

申请号：US13646325

申请日：2012-10-05

Applicant: Amazon Technologies, Inc.

Inventor： Sharadh Ramaswamy ,  David W. Stafford ,  Volodymyr V. Ivanchenko

IPC: H04N17/00 ,  H04N13/02

CPC classification number: G06T7/85 ,  G06T5/006 ,  G06T2207/10012 ,  H04N13/239 ,  H04N13/246

Abstract: The quality of stereoscopic imaging using cameras with wide angle lenses can be improved using various calibration approaches to determine distortions or misalignments between the cameras. A calibration object such as a checkered grid with a determined inclination between portions can be used to provide lateral calibration as well as depth information. Intersections of the checkered regions can be used to determine intersection points for the calibration object in the image. Lines formed by the checkered regions can be located, and the points correlated with these lines, in order to determine correspondence between points in the image. These points are mapped to corresponding points of the calibration object in the real world, to determine system parameters and/or image adjustments to be made when subsequent images are captured, in order to remove the distortions and misalignment when providing a stereo image based on images from the cameras.

Abstract translation: 使用各种校准方法可以改善使用具有广角镜头的相机的立体成像的质量，以确定相机之间的失真或不对准。 可以使用诸如在部分之间具有确定的倾斜度的方格网格的校准对象来提供横向校准以及深度信息。 方格区域的交点可用于确定图像中校准对象的交点。 可以定位由方格区域形成的线，并且这些点与这些线相关联，以便确定图像中的点之间的对应关系。 这些点被映射到现实世界中的校准对象的对应点，以确定当捕获后续图像时要进行的系统参数和/或图像调整，以便在基于图像提供立体图像时去除失真和未对准 从相机。

公开(公告)号：US09208548B1

公开(公告)日：2015-12-08

申请号：US13888247

申请日：2013-05-06

Applicant: Amazon Technologies, Inc.

Inventor： Isaac Scott Noble ,  David W. Stafford

IPC: G06K9/62 ,  G06T5/50

CPC classification number: G06T5/50 ,  G06F17/30 ,  G06T2207/20021 ,  G06T2207/20221

Abstract: Approaches are described for managing the processing of image and/or video data captured by an electronic device. A user can capture an image using a camera of a computing device, where metadata obtained by sensor(s) of the device can be stored along with the image. The image can be transmitted to a network service, where the network service can divide the image into a plurality of image portions, and for each image portion, the network service can search a library of image patches in attempt to find at least one library patch that substantially matches a respective image portion. If one of the library image portions matches the image portion within an allowable threshold, the network service can modify the image portion such as by applying image modifications made to the library image patch to the image portion or merging the library patch image with the image portion.

Abstract translation: 描述了用于管理由电子设备捕获的图像和/或视频数据的处理的方法。 用户可以使用计算设备的相机拍摄图像，其中可以与该图像一起存储由设备的传感器获得的元数据。 该图像可以被发送到网络服务，其中网络服务可以将图像划分成多个图像部分，并且对于每个图像部分，网络服务可以搜索图像片段库，以试图找到至少一个库片段 基本上匹配相应的图像部分。 如果库图像部分之一匹配图像部分在可允许的阈值内，则网络服务可以修改图像部分，例如通过对图像部分应用对库图像补丁进行的图像修改或者将库补丁图像与图像部分合并 。