Multi-aperture stereo reconstruction for artificial compound eye with cross image belief propagation.

Abstract

The artificial compound eye is a new type of camera that has miniature volume and large field of view (FOV), while the captured image is an array of sub-images, and each sub-image captures a part of the full FOV. To obtain a complete image with a full FOV, reconstruction is needed. Due to the parallax between adjacent sub-images, the reconstruction of images is depth related. In this paper, to address the image reconstruction of a specific artificial compound eye-eCley-a cross image belief propagation method is proposed to estimate the depth map. Since the small size and small FOV of the sub-image lead to little contextual information for pairwise matching, the information of neighboring sub-images is integrated into the belief propagation step to propagate the message across images. Therefore, the belief propagation step is able to gather as much information as needed from all the sub-images to obtain an accurate depth result. As a consequence, a stereo image with the full FOV and corresponding depth map can be obtained based on the estimated depth of sub-images. Experimental results on real data show the effectiveness of the proposed method.