公开(公告)号：US09111351B2

公开(公告)日：2015-08-18

申请号：US13688741

申请日：2012-11-29

Applicant: Linus Mårtensson

Inventor： Linus Mårtensson

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06T7/0075 ,  G06T7/73 ,  G06T2207/10012 ,  G06T2207/30244

Abstract: A device may obtain, from a camera associated with a reference object, depth image data including objects in a first frame and a second frame; identify features of the objects in the first frame and the second frame; and track movements of the features between the first frame and the second frame. The device may also identify independently moving features in the second frame, based on the tracking movements; remove the independently moving features from the depth image data to obtain a static feature set; and process the depth image data corresponding to the static feature set to detect changes in the relative position of objects in the first frame and the second frame. The processor may further translate the changes in relative position into corresponding movement data of the camera and provide the corresponding movement data to an inertial navigation system.

Abstract translation: 设备可以从与参考对象相关联的摄像机获得包括第一帧和第二帧中的对象的深度图像数据; 识别第一帧和第二帧中的对象的特征; 并跟踪第一帧和第二帧之间的特征的移动。 该装置还可以基于跟踪运动来识别第二帧中的独立运动特征; 从深度图像数据中移除独立移动的特征，获得静态特征集; 并且处理与静态特征集对应的深度图像数据，以检测第一帧和第二帧中的对象的相对位置的变化。 处理器可以进一步将相对位置的变化转换成相机的相应运动数据，并将相应的运动数据提供给惯性导航系统。

公开(公告)号：US09076269B2

公开(公告)日：2015-07-07

申请号：US13813187

申请日：2012-01-31

Applicant: Per Åstrand ,  Magnus Landqvist ,  Karl Ola Thörn ,  Mats Wernersson ,  Linus Mårtensson ,  Henrik Bengtsson

Inventor： Per Åstrand ,  Magnus Landqvist ,  Karl Ola Thörn ,  Mats Wernersson ,  Linus Mårtensson ,  Henrik Bengtsson

IPC: G06K9/36 ,  G06T11/60 ,  G06T3/40 ,  G06T5/50

CPC classification number: G06T11/60 ,  G06T3/4038 ,  G06T5/50 ,  G06T2207/10021 ,  G06T2207/20221 ,  G06T2207/20228

Abstract: An object of the present invention is to provide a way of improving the stitching procedure.The object is achieved by a method in an electronic device for creating a combined image. The method comprises obtaining (701) a first set of at least two sub-images recorded by an array camera. The method further comprises obtaining (702) a second set of at least two sub-images recorded by the array camera. A first depth map is calculated for the first set of sub-images. The first depth map comprises information about a first plane of the sub-images and a second plane of the sub-images. The first plane being at a first distance from the point where the sub-images have been recorded, and the second plane being at a second distance from the point where the sub-images have been recorded. A second depth map is calculated for the second set of sub-images. The second depth map comprises information about the first plane and the second plane. The method further comprises stitching the first set of sub-images and the second set of sub-images in the first plane, and thereby obtaining a first stitched image. The first set of sub-images and the second set of sub-images are stitched in the second plane, and thereby obtaining a second stitched image. Finally the method comprises combining the first stitched image with the second stitched image and thereby creating the combined image.

Abstract translation: 本发明的目的是提供一种改善缝合过程的方法。 该目的通过用于创建组合图像的电子设备中的方法来实现。 该方法包括获得（701）由阵列照相机记录的至少两个子图像的第一组。 该方法还包括获得（702）由阵列照相机记录的至少两个子图像的第二组。 对于第一组子图像计算第一深度图。 第一深度图包括关于子图像的第一平面和子图像的第二平面的信息。 第一平面处于与已经记录了子图像的点之间的第一距离处，并且第二平面处于距离已经记录了子图像的点的第二距离处。 针对第二组子图像计算第二深度图。 第二深度图包括关于第一平面和第二平面的信息。 该方法还包括在第一平面中缝合第一组子图像和第二组子图像，从而获得第一缝合图像。 第一组子图像和第二组子图像被缝合在第二平面中，从而获得第二缝合图像。 最后，该方法包括组合第一缝合图像和第二缝合图像，从而创建组合图像。