A Cognitive Control-Inspired Approach to Object Tracking

Under a tracking framework, the definition of the target state is the basic step for automatic understanding of dynamic scenes. More specifically, far object tracking raises challenges related to the potentially abrupt size changes of the targets as they approach the sensor. If not handled, size changes can introduce heavy issues in data association and position estimation. This is why adaptability and self-awareness of a tracking module are desirable features. The paradigm of cognitive dynamic systems (CDSs) can provide a framework under which a continuously learning cognitive module can be designed. In particular, CDS theory describes a basic vocabulary of components that can be used as the founding blocks of a module capable to learn behavioral rules from continuous active interactions with the environment. This quality is the fundamental to deal with dynamic situations. In this paper we propose a general CDS-based approach to tracking. We show that such a CDS-inspired design can lead to the self-adaptability of a Bayesian tracker in fusing heterogeneous object features, overcoming size change issues. The experimental results on infrared sequences show how the proposed framework is able to outperform other existing far object tracking methods.

[1]  Carlo S. Regazzoni,et al.  A bio-inspired system model for interactive surveillance applications , 2011, J. Ambient Intell. Smart Environ..

[2]  Ingemar J. Cox,et al.  A review of statistical data association techniques for motion correspondence , 1993, International Journal of Computer Vision.

[3]  Carlo S. Regazzoni,et al.  A switching fusion filter for dim point target tracking in infra-red video sequences , 2014, 17th International Conference on Information Fusion (FUSION).

[4]  Yu Zhang,et al.  A Scale Adaptive Method Based On Quaternion Correlation in Object Tracking , 2014, J. Comput..

[5]  Andrea Cavallaro,et al.  Tracker-Level Fusion for Robust Bayesian Visual Tracking , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Ying Li,et al.  Detecting and tracking dim small targets in infrared image sequences under complex backgrounds , 2012, Multimedia Tools and Applications.

[7]  Vladimir Pavlovic,et al.  A dynamic Bayesian network approach to figure tracking using learned dynamic models , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  H. Najjaran,et al.  Real-time monocular vision-based object tracking with object distance and motion estimation , 2010, 2010 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[11]  Askar Hamdulla,et al.  A Particle Filter Based Algorithm for State Estimation of Dim Moving Point Target in IR Image Sequence , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[12]  Huchuan Lu,et al.  Robust Visual Tracking via Least Soft-Threshold Squares , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Huchuan Lu,et al.  Inverse Sparse Tracker With a Locally Weighted Distance Metric , 2015, IEEE Transactions on Image Processing.

[14]  Gerd Wanielik,et al.  Unifying Bayesian networks and IMM filtering for improved multiple model estimation , 2009, 2009 12th International Conference on Information Fusion.

[15]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Fei Long,et al.  Adaptive kernel-bandwidth object tracking based on Mean-shift algorithm , 2013, 2013 Fourth International Conference on Intelligent Control and Information Processing (ICICIP).

[17]  Christian Lundquist,et al.  A Gaussian mixture PHD filter for extended target tracking , 2010, 2010 13th International Conference on Information Fusion.

[18]  Srini Narayanan,et al.  Learning all optimal policies with multiple criteria , 2008, ICML '08.

[19]  David Vernon,et al.  Cognitive Vision: the Case for Embodied Perception , 2005 .

[20]  Narendra Ahuja,et al.  Robust Visual Tracking Via Consistent Low-Rank Sparse Learning , 2014, International Journal of Computer Vision.

[21]  Simon Haykin,et al.  Cognitive Control: Theory and Application , 2014, IEEE Access.

[22]  D. Salmond,et al.  Spatial distribution model for tracking extended objects , 2005 .

[23]  Simon Haykin,et al.  Cognitive Dynamic Systems: Radar, Control, and Radio [Point of View] , 2012, Proc. IEEE.

[24]  Yvo Boers,et al.  A Track Before Detect Approach for Extended Objects , 2006, 2006 9th International Conference on Information Fusion.

[25]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Jean Dezert,et al.  Tracking maneuvering and bending extended target in cluttered environment , 1998, Defense, Security, and Sensing.

[27]  Simon Haykin,et al.  Cognitive Dynamic Systems , 2006, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[28]  I. White,et al.  Quantifying the impact of between-study heterogeneity in multivariate meta-analyses , 2012, Statistics in medicine.

[29]  Sriraam Natarajan,et al.  Dynamic preferences in multi-criteria reinforcement learning , 2005, ICML.

[30]  P. Zelazo,et al.  What is Cognitive Control , 2013 .

[31]  Uwe D. Hanebeck,et al.  Shape tracking of extended objects and group targets with star-convex RHMs , 2011, 14th International Conference on Information Fusion.

[32]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[33]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[34]  Vincenzo Lippiello,et al.  Visual motion estimation of 3D objects: an adaptive extended Kalman filter approach , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[35]  Bing Han,et al.  Robust feature-based object tracking , 2007, SPIE Defense + Commercial Sensing.

[36]  B. Baars,et al.  The Timing of the Cognitive Cycle , 2011, PloS one.

[37]  Yanjiang Wang,et al.  Tracking multi objects with different size based on data association , 2012, 2012 IEEE 11th International Conference on Signal Processing.

[38]  D. Zhang,et al.  Scale and orientation adaptive mean shift tracking , 2012 .

[39]  Alberto Del Bimbo,et al.  Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation , 2011, Comput. Vis. Image Underst..

[40]  R. Shumway,et al.  Dynamic linear models with switching , 1991 .

[41]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[42]  Lyudmila Mihaylova,et al.  Extended Object Tracking Using Monte Carlo Methods , 2008, IEEE Transactions on Signal Processing.

[43]  Jin Gao,et al.  Transfer Learning Based Visual Tracking with Gaussian Processes Regression , 2014, ECCV.

[44]  Y. Bar-Shalom,et al.  The probabilistic data association filter , 2009, IEEE Control Systems.

[45]  Gösta H. Granlund.  Does Vision Inevitably Have to be Active , 1998 .

[46]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[47]  X. Rong Li,et al.  Joint tracking and classification of extended object based on support functions , 2014, 17th International Conference on Information Fusion (FUSION).

[48]  Simon Haykin,et al.  On Cognitive Dynamic Systems: Cognitive Neuroscience and Engineering Learning From Each Other , 2014, Proceedings of the IEEE.

[49]  Konkoly Thege.  Multi-criteria Reinforcement Learning , 1998 .

[50]  Huchuan Lu,et al.  Visual Tracking via Weighted Local Cosine Similarity , 2015, IEEE Transactions on Cybernetics.