Fast Image Labeling for Creating High-Resolution Panoramic Images on Mobile Devices

We present an image labeling approach for merging a set of aligned source images into a composite image by finding optimal seams in the overlapping areas of the source images quickly and using little memory. A minimal-cost path in the overlapping area of two images is found by dynamic programming and used as an optimal seam to label images. The overlapping images are cut along the seam and merged together. A sequential image stitching procedure is integrated with the fast image labeling for producing high-resolution and high-quality panoramic images using large source images under limited computational and memory resources. The approach presents several advantages: the use of dynamic programming optimization for finding the minimal-cost path over adjacent source images guarantees finding the optimal seam and allows images to be merged quickly; ghosting and blurring problems caused by moving objects and small registration errors can be avoided by the optimal seam finding process; the combination of the sequential image stitching procedure with the fast image labeling allows processing large source images for creating high-resolution panoramic images using little memory; the fast labeling process is easy to combine with intensive blending to produce high-quality panoramic images. The method is implemented in our mobile panorama system and runs with good performance on mobile devices.

[1]  Richard Szeliski,et al.  Fast Poisson blending using multi-splines , 2011, 2011 IEEE International Conference on Computational Photography (ICCP).

[2]  David Salesin,et al.  Interactive digital photomontage , 2004, SIGGRAPH 2004.

[3]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[4]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .

[5]  Harry Shum,et al.  To appear in the ACM SIGGRAPH conference proceedings Drag-and-Drop Pasting , 2022 .

[6]  Natasha Gelfand,et al.  Efficient Extraction of Robust Image Features on Mobile Devices , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[7]  James Davis,et al.  Mosaics of scenes with moving objects , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[8]  Michael Kazhdan,et al.  Streaming multigrid for gradient-domain operations on large images , 2008, SIGGRAPH 2008.

[9]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[10]  Yingen Xiong,et al.  Gradient Domain Image Blending and Implementation on Mobile Devices , 2009, MobiCASE.

[11]  Bernd Girod,et al.  Outdoors augmented reality on mobile phone using loxel-based visual feature organization , 2008, MIR '08.

[12]  Bobby Bodenheimer,et al.  Synthesis and evaluation of linear motion transitions , 2008, TOGS.

[13]  Zeev Farbman,et al.  Coordinates for instant image cloning , 2009, ACM Trans. Graph..

[14]  Bernd Girod,et al.  Robust image retrieval using multiview scalable vocabulary trees , 2009, Electronic Imaging.

[15]  Dieter Schmalstieg,et al.  Robust and unobtrusive marker tracking on mobile phones , 2008, 2008 7th IEEE/ACM International Symposium on Mixed and Augmented Reality.

[16]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[17]  David L. Milgram,et al.  Computer Methods for Creating Photomosaics , 1975, IEEE Transactions on Computers.

[18]  Shmuel Peleg,et al.  Seamless Image Stitching in the Gradient Domain , 2004, ECCV.

[19]  Yingen Xiong,et al.  Mask-based image blending and its applications on mobile devices , 2009, International Symposium on Multispectral Image Processing and Pattern Recognition.

[20]  Mohammad H. Mahoor,et al.  Fast image blending using watersheds and graph cuts , 2009, Image Vis. Comput..