Creating full view panoramic image mosaics and environment maps
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
International Journal of Computer Vision
Bundle Adjustment - A Modern Synthesis
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Image Stitching - Comparisons and New Techniques
CAIP '99 Proceedings of the 8th International Conference on Computer Analysis of Images and Patterns
Using geometric corners to build a 2D mosaic from a set of image
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Automatic Mosaicing with Super-Resolution Zoom
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
Photographing long scenes with multi-viewpoint panoramas
ACM SIGGRAPH 2006 Papers
Camera-Based Document Image Mosaicing
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Automatic Panoramic Image Stitching using Invariant Features
International Journal of Computer Vision
Image alignment and stitching: a tutorial
Foundations and Trends® in Computer Graphics and Vision
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
Video Mosaics for Virtual Environments
IEEE Computer Graphics and Applications
Sequential image stitching for mobile panoramas
ICICS'09 Proceedings of the 7th international conference on Information, communications and signal processing
Fast Matching of Binary Features
CRV '12 Proceedings of the 2012 Ninth Conference on Computer and Robot Vision
| Hi-index | 0.00 |
A novel stitching method is presented that is capable of automatically determining the panorama type, planar or rotational, form a set of input images. The proposed method distinguishes between two kinds of panoramas, which we achieve through homography parametrization for the estimation of a global camera motion. The presented algorithm is part of a complete image stitching pipeline, where the determined panorama type is utilized for adaptive bundle adjustment with a matching number of degrees of freedom (DOFs). For planar scenes bundle adjustment for the homography's full eight DOFs are used, while three DOFs have proven to be sufficient for rotational panoramas. Knowledge about the panorama type yields significant advantages with regard to the selection of a mapping surface and the over all processing time and memory usage, which is especially import when being used on mobile devices such as smartphones, tablets, and digital cameras. For rotational panoramas, a spherical mapping surface is chosen, while a planar surface is suitable for a planar panorama. The resulting panorama image thus adequately represents the obseved scene in both cases, which cannot be achieved by current methods. The method was implemented on an iPhone 5S and tested on 50 scenes. Computation times for processing between 5 and 15 images for rotational and planar stitching ranged from 3 to 15 seconds with peak memory usage below 100 MB in all cases. The average reprojection error was slightly higher for rotational stitching but well below 1.5 pixels in each case.