Near-duplicate Fragments in Simultaneously Captured Videos - A Study on Real-time Detection using CBVIR Approach
Andrzej Sluzek
2016
Abstract
CBVIR approach to video-based surveillance is discussed. The objective is to detect in real time near-duplicates (e.g. similarly-looking objects) simultaneously appearing in concurrently captured/played videos. A novel method of keypoint matching is proposed, based on keypoint descriptions additionally incorporating visual and geometric contexts. Near-duplicate fragments can be identified by keypoint matching only. The analysis of geometric constraints (a bottleneck of typical CBVIR methods for sub-image retrieval) is not required. When the proposed method is fully implemented, high-speed and good performances can be achieved, as preliminarily shown in proof-of-concept experiments. The method is affine-invariant and employs typical keypoint detectors and descriptors (MSER and SIFT) as the low-level mechanisms.
References
- Zhao, W-L., Ngo, C-W., 2009. Scale-rotation invariant pattern entropy for keypoint-based near-duplicate detection. IEEE Trans. Image Proc., 18(2): 412-423.
- Chum, O., Perdoch, M., Matas, J., 2009. Geometric minhashing: Finding a (thick) needle in a haystack. Proc. IEEE Conf. CVPR'09: 17-24.
- Sivic, J., Zisserman. A., 2003. Video Google: A text retrieval approach to object matching in videos. Proc. 9th IEEE Int. Conf. ICCV'03: 1470-1477.
- Zhao, W.-L., Ngo, C.-W., Tan, H.-K. and Wu, X., 2007. Near-duplicate keyframe identification with interest point matching and pattern learning. IEEE Trans. Multimedia, 9(5): 1037-1048.
- Paradowski, M., Sluzek, A., 2010. Real-time retrieval of near- duplicate fragments in images and video-clips. Proc. ACIVS 2010 (LNCS 6474): 18-29.
- Romberg, S., August, M., Ries, Ch.X. and Lienhart, R., 2012. Robust Feature Bundling. Proc. PCM 2012 (LNCS 7674): 45-56.
- Tuytelaars, T., Mikolajczyk, K., 2008. Local inavariant feature detectors: A survey, Now Publishers Inc.
- Matas, J., Chum, O., Urban, M. and Pajdla, T., 2002. Robust wide baseline stereo from maximally stable extremal regions, Proc. BMVC'02: 384-393.
- Kristensen, F., MacLean, W.J., 2007. Real-time extraction of maximally stable extremal regions on an FPGA, Proc. IEEE Symp. ISCAS'07: 165-168.
- Salahat, E., Saleh, H., Sluzek, A., Al-Qutayri, M., Mohammed, B., and Ismail, M., 2016. Architecture and method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs), U.S. Patent 9,311,555.
- Cornelis, N., Van Gool, L., 2008. Fast scale invariant feature detection and matching on programmable graphics hardware, Proc. IEEE Conf. CVPR'08 Workshop: 1-8, 2008.
- Sluzek, A., 2012. Large vocabularies for keypoint-based representation and matching of image patches, Proc. ECCV'12 W&T (LNCS 7583): 229-238.
- Suzuki, T., 2012. SIFT-based low complexity keypoint extraction and its real-time hardware implementation for full-HD video, Proc. APSIPA'12 Annual Summit and Conf.: 1-6.
- Paschalakis, S., Lee, P. and Bober, M., 2003. An FPGA system for the high speed extraction, normalization and classification of moment descriptors, Proc. 13 Int. Conf. FPL'03 (LNCS 2778): 543-552.
- Nister, D., Stewenius, H., 2006. Scalable recognition with a vocabulary tree, Proc. IEEE Conf. CVPR'06: 2161- 2168.
- Jegou, H., Douze, M. and Schmid, C., 2010. Improving bag-of-features for large scale image search, Int. J. Comp. Vision 87(3): 316-336.
- Schmid, C., Mohr, R., 1997. Local grayvalue invariants for image retrieval. IEEE Trans PAMI 19(5): 530-534.
- Sluzek, A., 2014. Extended keypoint description and the corresponding improvements in image retrieval, Proc. ACCV 2014 Workshops, (LNCS 9008): 698-709.
- Flusser, J., Suk, T., 1993. Pattern recognition by affine moment invariants, Pattern Recognition 26: 167-174.
- Stewenius, H., Gunderson, S., Pilet, J., 2012. Size matters: Exhaustive geometric verification for image retrieval. Proc. ECCV'12 (LNCS 7573): 674-687.
Paper Citation
in Harvard Style
Sluzek A. (2016). Near-duplicate Fragments in Simultaneously Captured Videos - A Study on Real-time Detection using CBVIR Approach . In Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-758-198-4, pages 232-237. DOI: 10.5220/0005971902320237
in Bibtex Style
@conference{icinco16,
author={Andrzej Sluzek},
title={Near-duplicate Fragments in Simultaneously Captured Videos - A Study on Real-time Detection using CBVIR Approach},
booktitle={Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2016},
pages={232-237},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005971902320237},
isbn={978-989-758-198-4},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Near-duplicate Fragments in Simultaneously Captured Videos - A Study on Real-time Detection using CBVIR Approach
SN - 978-989-758-198-4
AU - Sluzek A.
PY - 2016
SP - 232
EP - 237
DO - 10.5220/0005971902320237