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

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.

[1]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[2]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[3]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[4]  Pascal Vasseur,et al.  Improvement of feature matching in catadioptric images using gyroscope data , 2008, 2008 19th International Conference on Pattern Recognition.

[5]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[6]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[7]  Selim Benhimane,et al.  Inertial sensor-aligned visual feature descriptors , 2011, CVPR 2011.

[8]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[9]  Edward Y. Chang,et al.  Inertial sensors aided image alignment and stitching for panorama on mobile phones , 2011, MLBS '11.

[10]  Edward Y. Chang,et al.  XINS: the anatomy of an indoor positioning and navigation architecture , 2011, MLBS '11.

[11]  Takeo Kanade,et al.  Inertial-aided KLT feature tracking for a moving camera , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.