Abstract
In this paper, we propose a robust visual tracking algorithm based on local dissimilarity map (LDM) and Kalman filter (KF). Firstly, we model the motion model component of the proposed tracker by using the KF. Then, we apply the LDM into the object matching model to measure the local dissimilarities between the target and the sampled candidates in each frame of the given image sequence. Experimental results on several image sequences illustrate that the proposed method performs well in several challenging aspects of real world scenes.
Similar content being viewed by others
REFERENCES
J.-F. Aujol, G. Gilboa, T. Chan, and S. Osher, “Structure-texture image decomposition—Modeling, algorithms, and parameter selection,” Int. J. Comput. Vision 67, 111–136 (2006). https://doi.org/10.1007/s11263-006-4331-z
E. Baudrier, “Comparaison d’images binaires reposant sur une mesure locale des dissimilarités. Application à la classification,” PhD Thesis (Université de Reims Champagne-Ardenne, Reims, 2005).
E. Baudrier, G. Millon, F. Nicolier, and S. Ruan, “Une méthode de comparaison d’images binaires quantifiant les dissimilarités locales Application à la classification d’impressions anciennes,” (2006), pp. 211–215.
É. Baudrier, F. Nicolier, G. Millon, and S. Ruan, “Binary-image comparison with local-dissimilarity quantification,” Pattern Recognit. 41, 1461–1478 (2008). https://doi.org/10.1016/j.patcog.2007.07.011
J. Black, T. Ellis, and P. Rosin, “Multi view image surveillance and tracking,” in Workshop on Motion and Video Computing, 2002, Orlando, Fla., 2002 (IEEE, 2002), pp. 169–174. https://doi.org/10.1109/MOTION.2002.1182230
Y. Ech-Choudany, “Analyse des signaux non-stationnaires à l’aide d’une nouvelle démarche de classification : application à l’identification de l’endommagement de matériaux composites par émission acoustique et à la détection de la crise d’épilepsie par EEG,” PhD Thesis (Université de Reims Champagne-Ardenne, Reims, 2018). http://www.theses.fr/2018REIMS020. Cited September 18, 2019.
S. Edelman, “Representation is representation of similarities,” Behav. Brain Sci. 21, 449–467 (1998). https://doi.org/10.1017/S0140525X98001253
G. Evangelopoulos and P. Maragos, “Image decomposition into structure and texture subcomponents with multifrequency modulation constraints,” in IEEE Conf. on Computer Vision and Pattern Recognition, Anchorage, Alaska, 2008 (IEEE, 2008), pp. 1–8. https://doi.org/10.1109/CVPR.2008.4587649
J. Giebel, D. M. Gavrila, and C. Schnörr, “A Bayesian framework for multi-cue 3D object tracking,” in Computer Vision–ECCV 2004, Ed. by T. Pajdla and J. Matas, Lecture Notes in Computer Science, vol. 3024 (Springer, Berlin, 2004), pp. 241–252. https://doi.org/10.1007/978-3-540-24673-2_20
J. Gilles, “Noisy image decomposition: A new structure, texture and noise model based on local adaptivity,” J. Math. Imaging Vision 28, 285–295 (2007). https://doi.org/10.1007/s10851-007-0020-y
S. Guo and X. Shi, “An improved spatiogram similarity measure for object tracking,” Pattern Recognit. Image Anal. 28, 79–86 (2018). https://doi.org/10.1134/S1054661818010169
H. Jabnoun, F. Benzarti, F. Morain-Nicolier, and H. Amiri, “Video-based assistive aid for blind people using object recognition in dissimilar frames,” Int. J. Adv. Intell. Paradigms 12, 122–139 (2019). https://doi.org/10.1504/IJAIP.2019.10010766
Y. Kim, B. Ham, M. N. Do, and K. Sohn, “Structure-texture image decomposition using deep variational priors,” IEEE Trans. Image Process. 28, 2692–2704 (2018). https://doi.org/10.1109/TIP.2018.2889531
N. Kumar and N. Sukavanam, “A cascaded CNN model for multiple human tracking and re-localization in complex video sequences with large displacement,” Multimedia Tools Appl. 79, 6109–6134 (2020). https://doi.org/10.1007/s11042-019-08501-4
I. Ketata, F. Morain-Nicolier, L. Sallemi, S. Ruan, and A. B. Hamida, “Localisation de tumeurs dans des séquences TEP, par détection de changements au moyen de dissimilarités locales,” in CORESA 2013 – 16ème édition du colloque COmpression et REprésentation des Signaux Audiovisuels, Le Creusot, France, 2013, pp. 183–188.
W. F. Leven and A. D. Lanterman, “Unscented Kalman filters for multiple target tracking with symmetric measurement equations,” IEEE Trans. Autom. Control 54, 370–375 (2009). https://doi.org/10.1109/TAC.2008.2008327
G. Mahfoudi, F. Morain-Nicolier, and F. Retraint, “Détection du copier-coller par mise en correspondance de descripteurs SIFT et filtrage à l’aide de cartes de dissimilarité locale,” p. 4.
I. S. Molchanov and P. Terán, “Distance transforms for real-valued functions,” J. Math. Anal. Appl. 278, 472–484 (2003). https://doi.org/10.1016/S0022-247X(02)00719-9
F. Morain-Nicolier, J. Landré, and S. Ruan, “Détection d’objet par mesure de dissimilarités locales,” in XXIIe colloque GRETSI (traitement du signal & des images), Dijon, 2009, vol. 1, p. 92.
F. Morain-Nicolier, J. Landré, and S. Ruan, “Gray level local dissimilarity map and global dissimilarity index for quality of medical images,” IFAC Proc. Vol. 42, 281–286 (2009). https://doi.org/10.3182/20090812-3-DK-2006.0073
Vermaak, Doucet, and Perez, “Maintaining multimodality through mixture tracking,” in Proc. Ninth IEEE Int. Conf. on Computer Vision, Nice, 2003 (IEEE, 2003), vol. 2, pp. 1110–1116. https://doi.org/10.1109/ICCV.2003.1238473
J. Wang, Y. Wang, C. Deng, and S. Wang, “Robust visual tracking based on convex hull with EMD-L1,” Pattern Recognit. Image Anal. 28, 44–52 (2018). https://doi.org/10.1134/S1054661818010078
Y. Wang, “Robust visual tracking based on relaxed target representation,” Pattern Recognit. Image Anal. 29, 415–424 (2019). https://doi.org/10.1134/S1054661819030210
E. Pekalska and R. P. W. Duin, Dissimilarity Representation for Pattern Recognition: Foundations and Applications, Series in Machine Perception and Artificial Intelligence, vol. 64 (World Scientific, 2005). https://doi.org/10.1142/5965
Y. Wu, J. Lim, and M.-H. Yang, “Online object tracking: A benchmark,” in IEEE Conf. on Computer Vision and Pattern Recognition, Portland, Ore., 2013 (IEEE, 2013), pp. 2411–2418. https://doi.org/10.1109/CVPR.2013.312
K. Yang, J. Wang, Z. Shen, Z. Pan, and W. Yu, “Application of particle filter algorithm based on Gaussian clustering in dynamic target tracking,” Pattern Recognit. Image Anal. 29, 559–564 (2019). https://doi.org/10.1134/S1054661819030106
Y. Zeng, X. Fu, L. Gao, J. Zhu, H. Li, and Y. Li, “Robust multivehicle tracking with Wasserstein association metric in surveillance videos,” IEEE Access 8, 47863–47876 (2020). https://doi.org/10.1109/ACCESS.2020.2978539
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
COMPLIANCE WITH ETHICAL STANDARDS
This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.
Conflict of Interest
The authors declare that they have no conflicts of interest.
Additional information
Wafae Mrabti is a PhD student in image processing at Faculty of Sciences of Sidi Mohamed Ben Abdellah University. She is member in ISAC Laboratory. Her research interests include image processing, pattern recognition, and artificial intelligence.
Benaissa Bellach received his PhD in 2003 from Université de Bourgogne, France. He is a professor at the National high School of Applied Sciences (ENSA) at Mohammed First University, Oujda, Morocco. His research interests include image processing, pattern recognition, machine learning, 3D profiling by structured light projection techniques, and CMOS retina.
Youssef Ech-Choudany received the engineering degree in electronics and computer science from National School of Applied Sciences, Oujda, Morocco, in 2013, and the PhD degree in signal processing from Université de Reims Champagne-Ardenne (France) and First Mohammed University (Morocco), in 2018. His research interests include signal processing, machine learning, and computer vision, with application on biomedical and acoustic emission signals.
Frédéric Morain-Nicolier received his PhD in 2000 from Université de Bourgogne, France. In 2001 he joined the CReSTIC of Université de Reims-Champagne-Ardenne and became full professor in 2010. His research interests include medical image processing, historical studies, image forensics, CBIR, local and non-metric similarties, and perceptual similarities.
Hamid Tairi received his PhD degree in 2001 from the University Sidi Mohamed Ben Abdellah, Morocco. In 2002 he has done a postdoc in the Image Processing Group of the Laboratory LE2I (Laboratoire d’Electronique, Informatique et Image) in France. Since 2003, he has been an associate professor at the University Sidi Mohamed Ben Abdellah, Morocco. He is the director of the ISAC Laboratory. His research interests are in visual tracking for robotic control, in 3D reconstruction of artificial vision, in medical image, and in visual information retrieval and pattern recognition.
Rights and permissions
About this article
Cite this article
Wafae Mrabti, Bellach, B., Ech-Choudany, Y. et al. Human Motion Tracking via the Local Dissimilarity Map. Pattern Recognit. Image Anal. 32, 162–173 (2022). https://doi.org/10.1134/S1054661822010047
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661822010047