Abstract
This paper issues the problem of moving object tracking in aerial video sequences for surveillance application. The proposed object tracking synthetic structure integrates edge correlation-based (EC) tracking algorithm and a novel regional mutual information-based (RMI) tracking algorithm. In this structure, using a novel defined crowded criterion, we are able to recognize a crowded background and vast difference of illumination. The proposed crowded criterion determines the crowded and non-crowded backgrounds based on two defined intensity variation and relative power measures that are calculated from four rectangular areas around the object. Due to inability of the EC tracking algorithm in tracking the object in the crowded frames, the RMI tracking algorithm is applied to track an object in the crowded frames of video sequences. Against, due to sensitivity of the RMI tracking algorithm to scale variations of the object and less computational complexity of the EC tracking algorithm, the EC tracking algorithm is selected for the object tracking in the non-crowded frames of the video sequences. However, the RMI tracking algorithm is suitable for the frames with the crowded backgrounds, high-intensity variations, noisy conditions, and existence of clutter, but it is sensitive to scale variations of the object. Moreover, it is normally slower than the EC tracking algorithm, but we apply Powell–Golden optimization method to optimize the RMI tracking algorithm, until we can use it as an online algorithm on each frame. The obtained results show the superiority of the proposed tracking structure in comparison with other conventional algorithms. Our proposed structure covers the most challenges of the tracking in the aerial surveillance application.
Similar content being viewed by others
References
Ahmed, J., Jafri, M.N., Shah, M., Akbar, M.: Real-time edge-enhanced dynamic correlation and predictive open-loop car following control for robust tracking. Mach. Vis. Appl. J. 19(1), 1–25 (2008)
Cui, Y., Samarasekera, S., Huang, Q., Greienhagen, M.: Indoor monitoring via the collaboration between a peripheral sensor and afoveal sensor, In: IEEE Workshop on Visual Surveillance, Bombay, pp. 2–9 (1998)
Alper, Y., Omar, J., Shah, M.: Object tracking: a survey tracking. ACM Comput Surv 38(4), 1–45 (2006)
Owens, J., Hunter, A., Fletcher, E.: A fast model-free morphology-based object tracking algorithm. In: British Machine Vision Conference, vol. 2, pp. 767–776 (2002)
Horn, B.K.P., Schunch, B.G.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)
Heeger, D.J.: Optical flow using spatiotemporal filters. Int. J. Comput. Vis. 1(4), 279–302 (1988)
Yilmaz, A., Li, X., Shah, M.: Contour-based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans. Pattern Anal. Mach. Int. 26(1), 1531–1536 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(7), 91–110 (2004)
Shi, J., Tomasi, C.: Good features to track. In: Proceedings of Computer Vision and Pattern Recognition. (CVPR), pp. 593–600, June 1994
Tomasi, C., Kanade, T.: Factoring image sequences into shape and motion. In: Proceedings the IEEE Workshop on Visual Motion, pp. 21–28 (1991)
Arivazhagan, S., Ganesan, L.: Automatic target detection using wavelet transform. EURASIP J. Appl. Signal Process. 17, 2663–2674 (2004)
Cho, J.S., Kim, D.J., Park, D.J.: Robust centroid target tracker based on new distance features in cluttered image sequences. IEICE Trans. Inf. Syst 83(12) (2000)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Int. 22(5), 603–619 (2002)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice-Hall, Inc., Englewood cliffs (2002)
Kuglin, C., Hines, D.: The phase correlation image alignment method. In: Proceedings International Conference on Cybernetics and Society, pp. 163–165 (1975)
Chien, S.I., Sung, S.H.: Adaptive window method with sizing vectors for reliable correlation-based target tracking. Pattern Recognit. 33(2), 237–249 (2000)
Lewis, J.P.: Fast normalized cross-correlation. Industrial Light & Magic (1995)
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Loza, A., Mihaylova, L., Bull, D.R., Canagarajah, C.N.: Structural similarity-based object tracking in multimodality surveillance videos. Mach. Vis. Appl. J. 20(2), 71–83 (2007)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Int. 6(1), 1–14 (2010)
Shannon, C.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379–423, 623–656 (1984)
Fleuret, F.: Fast binary feature selection with conditional mutual information. J. Mach. Learn. Res. 5, 1531–1555 (2004)
Soleimani, H., Khosravifard, M.: Reducing interpolation artifacts for mutual information based image registration. J. Med. Signals Sens. 1(3), 177–183 (2011)
Russakoff, D.B., Tomasi, C., Rohlng, T., Maurer, C.R.: Image similarity using mutual information of regions. ECCV 3, 596–607 (2004)
Asgarizadeh, M., Pourghassem, H., Shahgholian, G.: Robust object tracking using regional mutual information and normalized cross correlation. In: Proceedings 4th International Conference on Computational Intelligence and Communication Networks (CICN2012), 3–5 Nov, pp. 411–415. Mathura, Uttar Pradesh, India (2012)
Asgarizadeh, M., Pourghassem, H., Shahgholian, G., Soleimani, H.: Robust and real time object tracking using regional mutual information in surveillance and reconnaissance systems. In: Proceedings of 2011 IEEE 7th Iranian Conference on Machine Vision and Image Processing (MVIP2011), 16–17 Nov. 2011, Tehran, Iran, pp. 1–5
Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical Recipesian in C. Cambridge University Press, Cambridge (1992)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Asgarizadeh, M., Pourghassem, H. A robust object tracking synthetic structure using regional mutual information and edge correlation-based tracking algorithm in aerial surveillance application. SIViP 9, 175–189 (2015). https://doi.org/10.1007/s11760-013-0431-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-013-0431-8