INSPORAMA: INS-Aided Misalignment Correction in Feature-Based Panoramic Image Stitching

摘要

Feature-based image stitching, which aligns images with overlapping fields of view and then stitches them together, is a widely used panorama-construction technology. However, the current scale-, view- and illumination-invariant features can still result in misalignment because of occurrences of congruent or near-congruent features. We propose an INS (inertial navigation system) aided image-alignment method, named INSPORAMA, to reduce such misalignment. INSPORAMA improves image alignment accuracy by reducing both image area and the number of candidate feature-pairs to compare. Based on INSPORAMA, we have built an Android application, which is able to construct panoramic images in near real-time.