Abstract
Auto target detection and tracking has always been a challenging task for the researchers. The problem becomes worse, if the input video to tracking algorithm is itself unstabilized. This complex problem of auto target detection and tracking in an unstabilized video is not well addressed and solved in the literature. An algorithm is developed and presented in this paper to auto-stabilize the video, auto detect the target of interest followed by tracking. Global and local motion vectors are computed in the same algorithm simultaneously for frame stabilization and target tracking respectively. Speeded Up Robust Features (SURF) are used innovatively to compute Global Motion Vector (GMV) and Local Motion Vector (LMV) separately. The algorithm auto-detects the unstabilized parameters if any and stabilizes the video by moving the frame in opposite GMV direction with anti rotation. First four frames are used for detecting and training the target of interest, then only two very recent frames are used for auto-detection of target, hence algorithm is very fast and suitable for online real time applications. The algorithm has been experimentally verified and outperforms with bench marked visual tracking algorithms.
Similar content being viewed by others
References
Akhloufi MA (2010) Pan and tilt real-time target tracking. In: Proceedings of SPIE 7668, airborne intelligence, surveillance, reconnaissance system and applications VII, 76680K, Apr. 2010, https://doi.org/10.1117/12.849766
Babenko B, Yang Ming-Husuan B Serge (2011) Robust object tracking with online multiple instance learning. In: IEEE transactions on pattern analysis and machine intelligence, vol. 33, pp. 1619–1632. https://doi.org/10.1109/TPAMI.2010.226 (no. 8)
Battiato S, Bruna AR, Puglisi G (2010) A robust block-based image/video registration approach for mobile imaging devices. IEEE Trans Multimed 12(7):622–635
Bellaire RL, Kamen EW, Zabin SM (1995) New nonlinear iterated filter with applications to target tracking. In: Proceedings of SPIE, 2561, signal and data processing of small targets 1995. https://doi.org/1117/12.217701
Bhateja V, Urooj S, Pandey A, Ekuakille A, Misra M (2013) Improvement of masses detection in digital mammograms employing non-linear filtering. In: IEEE international mutli-conference on automation, computing, communication, control and compressed sensing (iMac4s), Kottayam, India, 22–23 March 2013, https://doi.org/10.1109/iMac4s.2013.6526445
Bin W, Yue-jin Z, De-Sen Y (2008) Image stabilization algorithm for digital image tracking. In: Proceedings of SPIE, vol. 6623, 66230Y, 2008. https://doi.org/10.1117/12.791425
Cao X, Jiang X, Li X, Yan P (2018) Correlation-based tracking of multiple targets with hierarchical layered structure. In: IEEE transactions on cybernetics, vol. 48, no. 1
Chen Z, You X, Boxuan Z, Jun L, Dacheng T (2017) Dynamically modulated mask sparse tracking. In: IEEE transactions on cybernetics, vol. 47, no. 11
Gupta P, Srivastava P, Bhardwaj S, Bhateja V (2011) A modified PSNR metric based on HVS for quality assessment of color images. In: IEEE international conference on communication and industrial application, West Bangal, India, 26–28 Dec 2011, https://doi.org/10.1109/ICCIndA.2011.6146669
Gupta P, Tripathi N, Bhateja V (2013) Multiple distortion pooling image quality assessment. Int J Converg Comput 1(1):60–72
Hao Q, Cheng X, Kang J, Jiang Y (2015) An image stabilization optical system using deformable freeform mirrors. Sensors 15:1736–1749. https://doi.org/10.3390/s150101736
Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. In: IEEE Transactions on Systems, Man and Cybernetics, vol. 34, no. 3
Jain A, Bhateja V (2011) A full-reference image quality metric for objective evaluation in spatial domain. In: International IEEE Conference on Communication and Industrial Application, pp. 1–5, 26 Dec 2011
Jain A, Singh Sonam, Vikrant B (2013) A robust approach for denoising and enhancement of mammographic images contaminated with high density impulse noise. Int J Converg Comput 1(1):38–49
Jalal AS, Singh V (2012) The state-of-the-art in visual object tracking. Informatica 36:227–248 2012)
Jia C, Evans BL (2017) Online motion smoothing for video stabilization via constrained multiple-model estimation. EURASIP J Image Video Process 2017:25. https://doi.org/10.1186/s13640-017-0171-8
Maheux J, Cruickshank JM (1998) Video-rate image stabilization system. In: Proceedings of SPIE, 3414, opto-contact:workshop on technology transfers, 24 Sept. 1998. https://doi.org/10.1117/12.323534
Maskell S, Rollason MP, Gordon NJ, Salmond DJ (2002) Efficient particle filtering for multiple target tracking with application to tracking in structured images. In: Proceedings of SPIE 4728, signal and data processing of small targets 2002. https://doi.org/10.1117/12.478509
Minmin W, Shengli S, Yejin Li (2018) A compressive tracking method based on gaussian differential graph and weighted cosine similarity metric. In: IEEE Signal Processing Letters, vol. 25, no. 4, Apr 2018
Pedersen Jacob Toft(2011) Study Group SURF: feature detection and description. In: Q4, pp 1–12, 2011
Puglisi G, Battiato S (2011) A robust image alignment algorithm for video stabilization purposes. IEEE Tran Circuits Syst Video Technol 21(10):1390–1400
Raj A, Srivsastava A, Bhateja V (2011) Computer aided detection of brain tumor in magnetic resonance images. In: IACSIT international journal of engineering and technology, vol. 3, no. 5, Oct 2011
Saad A, Shah M (2006) Tracking in aerial imagery. In: Proceedings of SPIE, 6209, airborne intelligence, surveillance, reconnaissance systems and applications III, 62090D, 2006. https://doi.org/10.1117/12.667266
Tsai T, Fang C, Chuang H (2012) Design and implementation of efficient video stabilization engine using maximum a posteriori estimation and motion energy smoothing approach. In: IEEE transaction on circuits and systems for video technology, Vol. 22, No. 6, June 2012
Verma K, Kumar A, Venkatesh KS, Gupta S (2014) Fast and robust real time digital video stabilization with smear removal using integral projection curve warping technique. In: IEEE, twentieth national conference on communications. https://doi.org/10.1109/NCC.2014.6811276
Verma K, Kumar A, Ghosh D (2018) Robust stabilised visual tracker for vehicle tracking. Def Sci J 68(3):307–315. https://doi.org/10.14429/dsj.68.12209
Wallha A, Wali A, Alimi AM (2014) Video stabilization with moving object detecting and tracking for aerial video surveillance. In: Springer, Multimedia Tools Appln. https://doi.org/10.1007/s11042-014-1928-z
Wang N (2018) A new approach for electronics image stabilization. In: Proceedings of SPIE, fourth seminar on novel optoelectronic detection technology and application, 106971G, Nanjing, China, 20 Feb 2018. https://doi.org/10.1117/12.2314589
Wu S, Zhang DC, Zhang Y, Basso J, Melle M (2012) Adaptive smoothing in real-time image stabilization. In: Proceedings of SPIE Vol. 8399 83990L-1, May 2012. https://doi.org/10.1117/12.918737
Xu J, Chang H, Yang S, Wang M (2012) Fast feature-based video stabilization without accumulative global motion estimation. IEEE Trans Consum Electron 58(3):993–999. https://doi.org/10.1109/TCE.2012.6311347
Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. In: ACM computing surveys, vol. 38, no. 4, Article 13, Dec 2006
Zhang K, Song H (2013) Real-time visual tracking via online weighted multiple instance learning. Pattern Recogn 46:397–411 (Jan 2013 (2013) 397–411 Issue 1)
Zhang K, Zhang L, Yang M-H (2012) Real-time compressive tracking. In: ECCV 2012, proceedings of the 12th European conference on computer vision, Vol. Part III, LNCS 7574, pp. 866–879, 2012,ISBN: 978-3-642-33711-6. https://doi.org/10.1007/978-3-642-33712-3_62
Zhang K, Zhang L, Yang M-H (2013) Real-time object tracking via online discriminative feature selection. IEEE Trans Image Process 22(12):4664–4677. https://doi.org/10.1109/TIP.2013.2277800 (Dec 2013)
Acknowledgements
Authors extend a deep sense of gratitude to Mr. Benjamin Lionel, Director, IRDE for encouragement and permission for publishing this work.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Verma, K., Ghosh, D. & Kumar, A. Visual tracking in unstabilized real time videos using SURF. J Ambient Intell Human Comput 15, 809–827 (2024). https://doi.org/10.1007/s12652-019-01249-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-019-01249-7