Abstract
The subject of mean shift algorithm for tracking the location of an object using a color model has recently gained considerable interest. However, the use of a color model to represent the tracked object is very sensitive to clutter interference, illumination changes, and the influence of background. Therefore, the applicability of basic color-based mean shift tracking is limited in many real world complex conditions. In this paper, we present a modified adaptive mean shift tracking algorithm integrating a combination of texture and color features. We first suggest a new texture-based target representation based on spatial dependencies and co-occurrence distribution within interest target region for invariant target description, which is computed through so-scaled Haralick texture features. Then, to improve the tracking further, we propose an extension to the mean shift tracker where a combination of texture and color features are used as the target model. To be consistent to the scale change and complex non-rigid motions of the tracked target, we suggest to adapt the tracking window of the proposed algorithm with the real moving target mask at tracking over time. Many experimental results demonstrate the successful of target tracking using the proposed algorithm in many complex situations, where the basic mean shift tracker obviously fails. The performance of the proposed adaptive mean shift tracker is evaluated using the VISOR video Dataset, thermal infrared-acquired images sequences bench mark, and also some proprietary videos.
Similar content being viewed by others
References
Yinghong, M., Zhi-Hong, M., Wenyan, J., Chengliu, L., Jiawei, Y., Mingui Sun, S.: Magnetic hand tracking for human-computer interface. IEEE Trans. Magn. 47, 970–973 (2011)
Bousetouane, F., Dib, L., Snoussi, H.: Robust detection and tracking pedestrian object for real time surveillance applications. Proc. SPIE 8285, 828508 (2011). doi:10.1117/12.913034
Souza, D.F.L., Machado, L.S., Moraes, R.M.: Integration of tracking systems for the development of virtual reality applications. IEEE Lat. Am. Trans. 8(6), 714–721 (2010)
Posada, L.F., Narayanan, K.K., Hoffmann, F., Bertram, T.: Floor segmentation of omnidirectional images for mobile robot visual navigation. In: Proc. Intelligent Robots and Systems IEEE/RSJ, pp. 804–809 (2010)
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), 1–45 (2006)
Zhang, C., Eggert, J.: A probabilistic method for hierarchical 2D-3D tracking. In: Proc. IEEE/IJCNN 2010, pp. 1–8 (2010)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–577 (2003)
Leichter, I., Lindenbaum, M., Rivlin, E.: Mean shift tracking with multiple reference color histograms. Comput. Vis. Image Underst. (CVIU) 114(3), 400–408 (2010)
Azghani, M., Aghagolzadeh, A., Ghaemi, S., Kouzehgar, M.: Intelligent modified mean shift tracking using genetic algorithm. In: Proc. 5th International Symposium on Telecommunications, pp. 806–811 (2010)
Ju, M.-Y., Ouyang, C.-S., Chang, H.-S.: Mean shift tracking using fuzzy color histogram. In: Proc. International Conference on Machine Learning and Cybernetics, pp. 2904–2908 (2010)
Peng, N., Yang, J., Liu, Z.: Mean shift blob tracking with kernel histogram filtering and hypothesis testing. Pattern Recognit. Lett. 26, 605–614 (2005)
Jeyakar, J., Babu, R.V., Ramakrishnan, R.K.: Robust object tracking using kernels and background information. In: Proc. IEEE International Conference on Image Processing, pp. 49–52 (2007)
Xiao, L., Li, P.: Improvement on mean shift based tracking using second-order information. In: Proc. IEEE 19th International Conference on Pattern Recognition, pp. 1–4 (2008)
Wang, J., Yagi, Y.: Integrating shape and color features for adaptive real-time object tracking. In: Proc. IEEE International Conference on Robotics and Biomimetics, pp. 1–6 (2006)
Xiang, Z., Dai, Y.M., Chen, Z.W., Zhang, H.X.: An improved Mean Shift tracking algorithm based on color and texture feature. In: Proc. Wavelet Analysis and Pattern Recognition, pp. 38–43 (2010)
Torralba, A., Oliva, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520–522 (2007)
Qi, G.-J., Hua, X.-S., Rui, Y., Tang, J., Zhang, H.-J.: Image classification with Kernelized spatial-context. IEEE Trans. Multimed. 12(4), 278–287 (2010)
Wu, Y., Fan, J.: Contextual flow. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (2009)
Surveillance Performance EValuation Initiative (SPEVI). http://www.eecs.qmul.ac.uk/~andrea/spevi.html
Fukunaga, K., Hostetle, L.D.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21, 32–40 (1975)
Qingchang, G., Xiaojuan, C., Hongxia, C.: Mean-shift of variable window based on the Epanechnikov Kernel. In: Proc. International Conference on Mechatronics and Automation, pp. 2314–2319 (2007)
Bekkari, A., Idbraim, S., Mammass, D., Yassa, M.: Exploiting spectral and space information in classification of high resolution urban satellites images using Haralick features and SVM. In: Proc. International Conference on Multimedia Computing and Systems, pp. 1–4 (2011)
Chitrakala, S., Shamini, P., Manjula, D.: Multi-class enhanced image mining of heterogeneous textual images using multiple image features. In: Proc. IEEE International Conference on Advance Computing, pp. 496–501 (2009)
Benz, U.C., Hofmann, P., Willhauck, G., Lingenfelder, I., Heynen, M.: Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J. Photogramm. Remote Sens. 58(3/4), 239–258 (2004)
Haralick, R.M., Shanmugam, K.: Computer classification of reservoir sandstones. IEEE Trans. Inf. Theory 11(4), 171–177 (1973)
Porebski, A., Vandenbroucke, N., Macaire, L.: Haralick feature extraction from LBP images for color texture classification. In: Proc. First Workshops on Image Processing Theory, Tools and Application, pp. 1–8 (2008)
Mao, K.Z., Wenyin, T.: Recursive Mahalanobis separability measure for gene subset selection. IEEE/ACM Trans. Comput. Biol. Bioinform. 8(1), 266–272 (2011)
OSU Thermal Pedestrian Database, OTCBVS Benchmark Dataset Collection. http://www.cse.ohio-state.edu/otcbvs-bench/
Video Surveillance Online Repository, VISOR Dataset Collection. http://imagelab.ing.unimore.it/visor/
PETS 2000 sequence. http://www.cs.berkeley.edu/~flw/tracker/pets2000.html
Schlogl, T., Beleznai, C., Winter, M., Bischof, H.: Performance evaluation metrics for motion detection and tracking. In: Proc. IEEE International Conference on Pattern Recognition, pp. 519–522 (2004)
Hao, W., Sankaranarayanan, A.C., Chellappa, R.: Online empirical evalua-tion of tracking algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1443–1458 (2010)
Wang, L., Zhang, Y., Feng, J.: On the Euclidean distance of images. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1334–1339 (2005)
Pan, P., Porikli, F., Schonfeld, D.: A new method for tracking performance evaluation based on a reflective model and perturbation analysis. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3529–3532 (2009)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bousetouane, F., Dib, L. & Snoussi, H. Improved mean shift integrating texture and color features for robust real time object tracking. Vis Comput 29, 155–170 (2013). https://doi.org/10.1007/s00371-012-0677-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-012-0677-0