Fast Adaptive Frame Preprocessing for 3D Reconstruction

Fabio Bellavia, Marco Fanfani, Carlo Colombo

2015

Abstract

This paper presents a new online preprocessing strategy to detect and discard ongoing bad frames in video sequences. These include frames where an accurate localization between corresponding points is difficult, such as for blurred frames, or which do not provide relevant information with respect to the previous frames in terms of texture, image contrast and non-flat areas. Unlike keyframe selectors and deblurring methods, the proposed approach is a fast preprocessing working on a simple gradient statistic, that does not require to compute complex time-consuming image processing, such as the computation of image feature keypoints, previous poses and 3D structure, or to know a priori the input sequence. The presented method provides a fast and useful frame pre-analysis which can be used to improve further image analysis tasks, including also the keyframe selection or the blur detection, or to directly filter the video sequence as shown in the paper, improving the final 3D reconstruction by discarding noisy frames and decreasing the final computation time by removing some redundant frames. This scheme is adaptive, fast and works at runtime by exploiting the image gradient statistic of the last few frames of the video sequence. Experimental results show that the proposed frame selection strategy is robust and improves the final 3D reconstruction both in terms of number of obtained 3D points and reprojection error, also reducing the computational time.

References

  1. Fanfani, M., Bellavia, F., Pazzaglia, F., and Colombo, C. (2013). SAMSLAM: Simulated annealing monocular SLAM. In Proc. of 15th International Conference on Computer Analysis of Images and Patterns, pages 515-522.
  2. Gherardi, R., Farenzena, M., and Fusiello, A. (2010). Improving the efficiency of hierarchical Structure-andMotion. In Proc. of Computer Vision and Pattern Recognition, pages 1594-1600.
  3. Joshi, N., Szeliski, R., and Kriegman, D. J. (2008). PSF estimation using sharp edge prediction. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition.
  4. Klein, G. and Murray, D. (2007). Parallel tracking and mapping for small AR workspaces. In Proc. of IEEE/ACM International Symposium on Mixed and Augmented Reality, pages 225-234.
  5. Klein, G. and Murray, D. (2008). Improving the agility of keyframe-based SLAM. In Proc. of 10th European Conference on Computer Vision, pages 802-815.
  6. Lee, H. S., Kwon, J., and Lee, K. M. (2011). Simultaneous localization, mapping and deblurring. In Proc. of IEEE International Conference on Computer Vision, pages 1203-1210.
  7. Liu, R., Li, Z., and Jia, J. (2008). Image partial blur detection and classification. In Proc. of Computer Vision and Pattern Recognition.
  8. Mei, C. and Reid, I. (2008). Modeling and generating complex motion blur for real-time tracking. In Proc. of Computer Vision and Pattern Recognition.
  9. Seo, Y., Kim, S., Doo, K., and Choi, J. (2008). Optimal keyframe selection algorithm for three-dimensional reconstruction in uncalibrated multiple images. Optical Engineering, 47(5):053201-053201-12.
  10. Snavely, N., Seitz, S. M., and Szeliski, R. (2008). Skeletal graphs for efficient structure from motion. In Proc. of Computer Vision and Pattern Recognition, pages 1-8.
  11. Szeliski, R. (2010). Computer Vision: Algorithms and Applications. Springer-Verlag New York, Inc., 1st edition.
  12. Tong, H., Li, M., Zhang, H., and Zhang, C. (2004). Blur detection for digital images using wavelet transform. In Proc. of IEEE International Conference on Multimedia & Expo, pages 17-20.
  13. Wu, C. (2013). Towards linear-time incremental structure from motion. In Proc. of Joint 3DIM/3DPVT Conference. http://ccwu.me/vsfm/.
Download


Paper Citation


in Harvard Style

Bellavia F., Fanfani M. and Colombo C. (2015). Fast Adaptive Frame Preprocessing for 3D Reconstruction . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 260-267. DOI: 10.5220/0005272702600267


in Bibtex Style

@conference{visapp15,
author={Fabio Bellavia and Marco Fanfani and Carlo Colombo},
title={Fast Adaptive Frame Preprocessing for 3D Reconstruction},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={260-267},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005272702600267},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Fast Adaptive Frame Preprocessing for 3D Reconstruction
SN - 978-989-758-091-8
AU - Bellavia F.
AU - Fanfani M.
AU - Colombo C.
PY - 2015
SP - 260
EP - 267
DO - 10.5220/0005272702600267