RECONSTRUCTION OF IMAGES FROM AN IN VIVO MULTI-CAMERA CAPSULE

摘要

Method and apparatus of reconstruction of images from an in vivo multi-camera capsule are disclosed. In one embodiment of the present invention, the capsule comprises two cameras with overlapped fields of view (FOVs). Intra-image based pose estimation is applied to the sub-images associated with the overlapped area to improve the pose estimation for the capsule device. In another embodiment, two images corresponding to the two FOVs are fused by using disparity-adjusted, linear weighted sum of the overlapped sub-images. In yet another embodiment, the images from the multi-camera capsule are stitched for time-space representation.

主权项

1. A method of displaying images of human gastrointestinal (GI) tract captured using a capsule device including a plurality of cameras, wherein the plurality of cameras are configured fixedly within a capsule housing and any two neighboring cameras of the plurality of cameras have an overlapped field of view (FOV), the method comprising:
receiving a plurality of image sequences captured by the plurality of cameras respectively, wherein the plurality of image sequences comprise multiple sets of intra images and an i-th set of intra images corresponds to concurrent images captured by the plurality of camera at time index i; generating a composite image by stitching the multiple sets of intra images; and displaying the composite image on a display device.