Abstract
Image mosaic is a useful preprocessing step for background subtraction in videos recorded by a moving camera. To avoid the ghosting effect and mosaic failure due to huge exposure difference and big parallax between adjacent images, this paper proposes an effective mosaic algorithm named Combined SIFT and Dynamic Programming (CSDP). Based on SIFT matching and dynamic programming, CSDP uses an improved optimal seam searching criterion that provides “protection mechanisms” for moving objects with an edge-enhanced weighting intensity difference operator and ultimately solves the ghosting and incomplete effect induced by moving objects. The proposed method was compared to three widely used mosaic softwares (i.e., AutoStitch, Microsoft ICE, and Panorama Maker) and Mills’ approach in multiple scenes. Experimental results show the feasibility and effectiveness of the proposed method.
Similar content being viewed by others
References
Bouwmans, T.: Recent advanced statistical background modeling for foreground detection: a systematic survey. Recent Pat. Comput. Sci. 4(3), (2011)
Brown, M., Lowe, D.: Recognising panorama. In: Proceedings of international conference on computer vision, pp. 1218–1225 (2003)
Davis, J.: Mosaics of scenes with moving objects. In: Proceedings of international conference on computer vision and, pattern recognition, pp. 354–360 (1998)
Debevec, P., Malik, J.: Recovering high dynamic range radiance maps from photographs. In: Proceedings of the 24th annual conference on computer graphics and interactive, techniques, pp. 369–378 (1997)
Dijkstra, E.W.: A note on two problems in connexion with graphs. NUMERISCHE MATHEMATIK 1(1), 269–271 (1959)
Duplaquet, M.: Building large image mosaies with invisible sema-lines. In: Proceedings of SPIE aerosense, pp. 369–377 (1998)
Echigo, T., Radke, R., Ramadge, P., Miyamori, H., Lisaku, S.: Ghost error elimination and superimposition of moving objects in video mosaicing. Proc. Int. Conf. Image Process. 4, 128–132 (1999)
Farcas, D., Marghes, C., Bouwmans, T.: Background subtraction via incremental maximum margin criterion: a discriminative subspace approach. Mach. Vis. Appl. 23(6), 1083–1101 (2012)
Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Garg, R., Seitz, S.M.: Dynamic mosaics. 3DIMPVT 2012, pp. 65–72 (2012)
Hartley, R., Zisserma, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2004)
He, Y., Chung, R.: Image mosaicking for polyhedral scene and in particular singly visible surfaces. Pattern Recogn. 41(3), 1200–1213 (2008)
Irani, M., Anandan, P., Bergen, J., Kumar, R., Hsu, S.: Efficient representations of video sequences and their applications. Signal Process. Image Commun. 8, 327–351 (1996)
Jia, J., Tang, C.K.: Eliminating structure and intensity misliagnment in image stitching. In: Proceedings of international conference on computer vision, pp. 1651–1658 (2005)
Kohandani, A., Basir, O., Kamel, M.: A fast algorithm for template matching. Image Anal. Recogn. 4142, 398–409 (2006)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Mann, S., Piccard, R. : Being ‘undigital’ with digital cameras: extending the dynamic range by combining differently exposed pictures. In: Proceedings of the 4th Annual Conference on IS &T, pp. 422–428 (1995)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)
Mills, A., Dudek, G.: Image stitching with dynamic elements. Image Vis. Comput. 27(10), 1593–1602 (2009)
Mitsunaga, T., Nayar, S.: Radiometric self calibratio. In: Proceedings of international conference on computer vision and, pattern recognition, pp. 374–380 (1999)
Shum, H., Szeliski, R.: Construction of panoramic image mosaics with global and local alignment. Int. J. Comput. Vis. 36(2), 101–130 (2000)
Szeliski, R.: Image alignment and stitching: a tutorial. Found. Trends Comput. Gr. Vis. 2(1), 1–105 (2006)
Szeliski, R., Shum, H.: Creating full view panoramic image mosaics and environment mapsn. In: Proceedings of the 24th annual conference on computer graphics and interactive, techniques, pp. 251–258 (1997)
Zeng, L., Deng, D., Chen, X., Zhang, Y.: A self-adaptive and real-time panoramic video mosaicing system. J. Comput. 7(1), 218–225 (2012)
Zhang, S., Yao, H., Liu, S.: Dynamic background subtraction based on local dependency histogram. Int. J. Pattern Recogn. Artif. Intell. 23(7), 1397–1419 (2009)
Zhang, S., Yao, H., Sun, X., Lu, X.: Sparse coding based visual tracking: Review and experimental comparison. Pattern Recogn. 46(7), 1772–1788 (2013a)
Zhang, S., Yao, H., Zhou, H., Sun, X., Liu, S.: Robust visual tracking based on online learning sparse representation. Neurocomputing 100(1), 31–40 (2013b)
Zhao, L., Yang, Y.: Mosaic image method: a local and global method. Pattern Recogn. 32(8), 1421–1433 (1999)
Zhou, H., Liu, T., Lin, F., Pang, Y., Wu, J., Wu, J.: Towards efficient registration of medical images. Comput. Med. Imaging Gr. 31(6), 374–382 (2007)
Zhou, H., Green, P.R., Wallace, A.M.: Estimation of epipolar geometry by linear mixed-effect modelling. Neurocomputing 72(16–18), 3881–3890 (2009)
Acknowledgments
This work was supported in part by Natural Science Foundation of China (No. 61300111) and Natural Scientific Research Innovation Foundation in Harbin Institute of Technology (HIT. NSRIF. 2014137). Jun Zhang was supported by Natural Science Foundation of China (No. 61273237).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zeng, L., Zhang, S., Zhang, J. et al. Dynamic image mosaic via SIFT and dynamic programming. Machine Vision and Applications 25, 1271–1282 (2014). https://doi.org/10.1007/s00138-013-0551-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-013-0551-8