Abstract
Inter-camera registration in multi-view systems with overlapped views has a particularly long and sophisticated research history within the computer vision community. Moreover, when applied to Distributed Video Coding, in systems with at least one moving camera it represents a real challenge due to the necessary data at decoder for generating the side information without any a priori knowledge of each instant camera position. This paper proposes a solution to this problem based on successive multi-view registration and motion compensated extrapolation for on-the-fly re-correlation of two views at decoder. This novel technique for side information generation is codec-independent, robust and flexible with regard to any free motion of the cameras. Furthermore, it doesn’t require any additional information from encoders nor communication between cameras or offline training stage. We also propose a metric for an objective assessment of the multi-view correlation performance.
Similar content being viewed by others
References
Aaron A, Girod B (2004) Wyner-ziv video coding with low encoder complexity. In: Proceedings international picture coding symposium, PCS’04, San Francisco
Aaron A, Rane S, Girod B (2004) Wyner-ziv video coding with hash-based motion-compensation at the receiver. In: Proceedings IEEE intl. conference on image processing, Singapore
Althof R, Wind M, Dobbins IJT (1997) A rapid and automatic image registration algorithm with subpixel accuracy. IEEE Trans Med Imag 16(3):308–316
Artigas X, Angeli E, Torres L (2006) Side information generation for multiview distributed video coding using a fusion approach. In: 7th nordic signal processing symposium, NORSIG’06, Reykjavik, Iceland, 7–9 June 2006
Ascenso J, Pereira F (2007) Adaptive hash-based side information exploitation for efficient Wyner-Ziv video coding. In: International conference on image processing (ICIP)—2007, San Antonio
Benedek C, Havasi L, Sziranyi T, Szlavik Z (2005) Motion-based flexible camera registration. Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on, pp 439–444
Bergevin R, Soucy M, Gagnon H, Laurendeau D (1996) Towards a general multi-view registration technique. IEEE Trans Pattern Anal Mach Intell 18(50):540–547
Brivio PA, Della Ventura A, Rampini A, Schettini R (1992) Automatic selection of control-points from shadows structures. Int J Remote Sens 13(10):1853–1860
Brown LG (1992) A survey of image registration techniques. ACM Comput Surv 24(4):325–376
Brown M, Lowe DG (2003) Recognising panoramas. In: Proceedings IEEE international conference on computer vision, Nice, 13–16 October 2003
Brown M, Lowe DG (2007) Automatic panoramic image stitching using invariant features. Int J Comput Vis 74:59–73
Cheng S, Xiong Z (2005) Successive refinement for the Wyner-Ziv problem and Layered Code Design. IEEE Trans Signal Process 53:8
Dufaux F, Ouaret M, Ebrahimi T (2007) Recent advances in multiview distributed video coding. In: SPIE defense and security symposium (DSS 2007), Orlando, 9–13 April 2007
Fonseca LMG, Costa MHM (1997) Automatic registration of satellite images. In: Brazilian symposium on computer graphics and image processing, 10, Campos de Jordão, pp 219–226
Forssén P-E, Lowe DG (2007) Shape descriptors for maximally stable extremal regions. In: International conference on computer vision (ICCV), Rio de Janeiro
Goncalves H, Goncalves JA, Corte-Real L (2008) Automatic image registration based on correlation and hough transform. In: Bruzzone L, Notarnicola C, Posa F (eds) SPIE, vol 7109, no 1, p 71090J. http://link.aip.org/link/?PSI/7109/71090J/1
Gordon I, Lowe DG (2006) What and where: 3D object recognition with accurate pose. Toward Category-Level Object Recognition, pp 67–82
Growe S, Tönjes R (1997) A knowledge based approach to automatic image registration. In: International conference on image processing 97, pp 26–29
Guo X, Lu Y, Wu F, Gao W, Li S (2006) Distributed multi-view video coding. In: Proceedings of SPIE-IS&T electronic imaging, SPIE, vol 6077, San Jose, 15–19 January 2006
Izquierdo E (2003) Efficient and accurate image based camera registration. IEEE Trans Multimedia 5(3):293–302
Le Moigne J, Xia W, Chalermwat P, El-Ghazawi T, Mareboyana M, Netanyahu N, Tilton J, Campbell W, Cromp R (1998) First evaluation of automatic image registration methods. In: Geoscience and remote sensing symposium proceedings, 1998. IGARSS ’98, vol 1. IEEE International, Piscataway, pp 315–317
Likar B, Pernus F (1999) Automatic extraction of corresponding points for the registration of medical images. Med Phys 26:1678–1686
Lowe D. Scale-Invariant Feature Transform (SIFT): matching with local invariant features. http://www.cs.ubc.ca/spider/lowe/research.html, http://www.cs.ubc.ca/~lowe/keypoints/
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110
Ouaret M, Dufaux F, Ebrahimi T (2006) Fusion-based multiview distributed video coding. In: ACM international workshop on video surveillance and sensor networks, Santa Barbara, 27 October 2006
Ouaret M, Dufaux F, Ebrahimi T (2007) Multiview distributed video coding with encoder driven fusion. In: European conference on signal processing (EUSIPCO), Poznan, 3–7 September 2007
Puri R, Ramchandran K (2003) PRISM: a “reversed” multimedia coding paradigm. In: Proceedings international conference on image processing (ICIP), Barcelona
Slepian D, Wolf JK (1973) Noiseless coding of correlated information sources. IEEE Trans Inf Theory 19:471–480
Szlavik Z, Sziranyi T, Havasi L (2007) Video camera registration using accumulated co-motion maps. 61(5):298–306
Tipdecho T (2002) Automatic image registration between image and object spaces. In: Proceedings of the open source GIS—GRASS users conference 2002, Trento, 11–13 September 2002
Wyner D, Ziv J (1976) The rate-distortion function for source coding with side information at the decoder. IEEE Trans Inf Theory 22:1–10
Yeo C, Ramchandran K (2007) Robust distributed multi-view video compression for wireless camera networks. In: VCIP 2007, San Jose, 28 January–1 February 2007
Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21(11):977–1000. doi:10.1016/S0262-8856(03)00137-9
Acknowledgement
The first author acknowledges the Fundação para a Ciência e a Tecnologia, Portugal, for the financial support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ciobanu, L., Côrte-Real, L. Successive refinement of side information for multi-view distributed video coding. Multimed Tools Appl 48, 411–436 (2010). https://doi.org/10.1007/s11042-009-0315-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-009-0315-7