Abstract
This paper presents a novel and fast method for k-means clustering based object tracking for coloured frames, based on histogram back-projection method. The proposed method uses histogram equalization for finding centroid of the object for each frame. As from the information transfer aspect, this study improves the tracking performance using Bhattacharya Coefficient with the method of histogram back-projection including k-means clustering. Histogram back-projection computes the probability of the object of interest and the clustering process classifies high-performance regions. In addition, a mean shift tracking method is used to monitor the object after the histogram back-projection process, which provides better tracking for fast-moving objects. The proposed mean shift algorithm also provides gradient ascent. In addition, this method is invariant to clutter and camera motion; pose changes and faster tracking. Simulated results show that the proposed method gives better tracking results than other conventional methods while having a lower computational demand. Therefore it is highlighted that the proposed method would have a significant contribution in the field of object tracking.
Similar content being viewed by others
References
Ahmad R, Tichadou S, Hascoet JY (2012) New computer vision based snakes and ladders algorithm for the safe trajectory of two axis CNC machines. Comput Aided Design 44:355–366
Avidan S (2005) Ensemble tracking. In: 2005 I.E. computer society conference on computer vision and pattern recognition; 20–25 June 2005; San Diego, USA: IEEE. pp. 494–501
Ayed IB, Chen H, Punithakumar K, Ross I, Li S (2012) Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure. Med Image Anal 16:87–100
Balasubramanian VK, Manavalan K (2016) Knowledge-based genetic algorithm approach to quantization table generation for the JPEG baseline algorithm. Turk J Electr Eng Comput Sci 24:1615–1635
Bhattacharyya A (1943) On a measure of divergence between two statistical populations defined by their probability distributions. Bull Calcutta Math Soc 35:99–109
Cao J, Wu Z, Wu J, Liu W (2013) Towards information-theoretic k-means clustering for image indexing. Signal Process 93:2026–2037
Cheng TY, Herman C (2014) Motion tracking in infrared imaging for quantitative medical diagnostic applications. Infrared Phys Technol 62:70–80
Cui J, Liu Y, Xu Y, Zhao H, Zha H (2013) Tracking generic human motion via fusion of low-and high-dimensional approaches. IEEE Trans Syst Man Cybern Syst 43(4):996–1002
Dai S, Lu K, Dong J, Zhang Y, Chen Y (2015) A novel approach of lung segmentation on chest CT images using graph cuts. Neurocomputing 168:799–807
Enkelmann W (2001) Video-based driver assistance: from basic functions to applications. Int J Comput Vis 45:201–221
Finlayson G, Hordley S, Schaefer G, Tian GY (2005) Illuminant and device invariant colour using histogram equalization. Pattern Recogn 38:179–190
Ghassabeh YA, Linder T, Takahara G (2013) On some convergence properties of the subspace constrained mean shift. Pattern Recogn 46:3140–3147
Goceri E, Unlu MZ, Dicle O (2015) A comparative performance evaluation of various approaches for liver segmentation from SPIR images. Turk J Electr Eng Comput Sci 23:741–768
Horn BKP (1986) Robot vision. 1st ed. MIT Press, Cambridge
Hsieh PC, Tung PC (2010) Shadow compensation based on facial symmetry and image average for robust face recognition. Neurocomputing 73:2708–2717
Hu M (1962) Visual pattern recognition by moment invariants. IRE Trans Inform Theory 8:179–187
Hu W, Sun Y, Li X, Jiang Y, Yu M (2016) Cam-shift target tracking approach based on back projection method with distance weights. 2016 International Conference on In Wavelet Analysis and Pattern Recognition (ICWAPR); 10–13 July 2016; Jeju Island, South Korea: IEEE. pp. 252–257
Intille SS, Davis JW, Bobick, AF (1997) Real-time closed-world tracking. In: 1997 I.E. computer society conference on computer vision and pattern recognition; 17–19 Jun 1997; Los Alamitos, California, USA: IEEE. pp. 697–703
Jian M, Jung C, Shen Y, Liu J (2015) Interactive image retrieval using constraints. Neurocomputing 161:210–219
Khalid MS, Ilyas MU, Sarfanaz MS, Ajaz MA (2006) Bhattacharyya coefficient in correlation of gray-scale objects. J Multimed 1:56–61
Klette R, Zunic J (2012) ADR shape descriptor – distance between shape centroids versus shape diameter. Comput Vis Image Und 116:690–697
Lautissier J, Legrand L, Lalande A, Walker P, Brunotte F (2003) Object tracking in medical imaging using a 2D active mesh system. Proceedings of the 25th Annual International Conference of the IEEE BMBS; 17–21 Sept. 2003; Cancun, Mexico: IEEE. pp. 739–742
Leichter I, Lindenbaum M, Rivlin E (2010) Mean shift tracking with multiple reference color histograms. Comput Vis Image Und 114:400–408
Li J, Li X, Tao D (2005) KPCA for semantic object extraction in images. Pattern Recogn 41:3244–3250
Li SX, Chang HX, Zhu CF (2010) Adaptive pyramid mean shift for global real-time visual tracking. Image Vis Comput 28:424–437
Li M, Zhao C, Tang J (2013) Hybrid image summarization by hypergraph partition. Neurocomputing 119:41–48
Lin C, Chen C, Lee H, Liao J (2014) Fast k-means algorithm based on a level histogram for image retrieval. Expert Syst Appl 41:3276–3283
Liu Y, Nie L, Liu L, Rosenblum DS (2016) From action to activity: sensor-based activity recognition. Neurocomputing 181:108–115
Lu N, Freng Z (2008) Mathematical model of blob matching and modified Bhattacharyya coefficient. Image Vis Comput 26:1421–1434
Lu Y, Wei Y, Liu L, Zhong J, Sun L, Liu Y (2017) Towards unsupervised physical activity recognition using smartphone accelerometers. Multimedia Tools and Applications 76(8):10701–10719
Martínez BA, Jiménez JJ (2011) Tracking by means of geodesic region models applied to multidimensional and complex medical images. Comput Vis Image Und 115:1083–1098
Qi S, Yu JG, Ma J, Li Y, Tian J (2015) Salient object detection via contrast information and object vision organization cues. Neurocomputing 167:390–405
Quine BM, Tarasyuk V, Mebrahtu H, Hornsey R (2007) Determining star-image location: a new sub-pixel interpolation technique to process image centroids. Comput Phys Commun 177:700–706
Sim KS, Tso CP, Tan YY (2007) Recursive sub-image histogram equalization applied to gray scale images. Pattern Recogn Lett 28:1209–1221
Simakov D, Caspi Y, Shechtman E, Irani M (2008) Summarizing visual data using bidirectional similarity. In: 2008 I.E. conference on computer vision and pattern recognition; 23–28 June 2008; anchorage, Alaska, USA: IEEE. pp. 1–8
Singhal N, Lee YY, Kim CS, Lee SU (2009) Robust image watermarking using local Zernike moments. J Vis Commun Image R 20:408–419
Tsai DM, Lin MC (2013) Machine-vision-based identification for wafer tracking in solar cell manufacturing. Robot Cim-Int Manuf 29:312–321
Wang F, Yu S, Yang J (2010) Robust and efficient fragments-based tracking using mean shift. AEU-Int J Electron C 64:614–623
Xie, X., Zaitsev, Y., Velasquez-Garcia, L., Teller, S., & Livermore, C. (2014). Compact, scalable, high-resolution, MEMS-enabled tactile displays. In Proc. of Solid-State Sensors, Actuators, and Microsystems Workshop; 8–12 June 2014; Hilton Head Island, USA: SC. pp. 127–130
Yao A, Wang G, Lin X, Chai X (2010) An incremental Bhattacharyya dissimilarity measure for particle filtering. Pattern Recogn 43(4):1244–1256
Yu J, Wang Z (2017) A video-based facial motion tracking and expression recognition system. Multimedia Tools and Applications 76(13):14653–14672
Acknowledgments
This study was performed at Gazi University, Engineering Faculty, Electrical & Electronics Engineering Department. Uğurhan KUTBAY performed the K-Mean process and Bhattacharyya Coefficient. In addition, Uğurhan KUTBAY discussed & reported the images and participated in the sequence alignment and drafted the manuscript with İsa ŞAHİN. Anıl AKYEL and Fırat HARDALAÇ created the study hypothesis with Uğurhan KUTBAY and helped to draft the manuscript. İsa ŞAHIN participated in the alignment sequence and evaluated the algorithms. The final editing of manuscript is carried out by Anıl AKYEL. All authors read and approved the final manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hardalaç, F., Kutbay, U., Şahin, İ. et al. A novel method for robust object tracking with K-means clustering using histogram back-projection technique. Multimed Tools Appl 77, 24059–24072 (2018). https://doi.org/10.1007/s11042-018-5661-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-5661-x