Adaptive Tobit Kalman-Based Tracking

This paper presents an online, real-time, multiobject tracking algorithm based on a novel method for data association. Tracking multiple objects in real-world scenes includes several challenges, such as a) object detectors with low detection accuracy, b) false alarms, and c) unmatched tracked objects. In this paper, we propose a novel filtering method based on the theory of censored data by utilizing an Adaptive Tobit Kalman filter to estimate the object's position with high accuracy. Furthermore, in order to deal with false alarms and unmatched tracked objects, we use the nonmaximum suppression and a modified Hungarian algorithm, respectively. Experiments in public datasets show that the proposed method outperforms state of the art methods in multi-object tracking with a substantial low computational cost compared to other methods in the area.

[1]  P. Daras,et al.  USING KALMAN FILTER AND TOBIT KALMAN FILTER IN ORDER TO IMPROVE THE MOTION RECORDED BY KINECT SENSOR II , 2016 .

[2]  Francois Bremond,et al.  Multi-Object tracking using multi-channel part appearance representation , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[3]  Bonhwa Ku,et al.  Online multi-person tracking with two-stage data association and online appearance model learning , 2016, IET Comput. Vis..

[4]  Bohyung Han,et al.  Multi-object Tracking with Quadruplet Convolutional Neural Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  S. Liberty,et al.  Linear Systems , 2010, Scientific Parallel Computing.

[6]  Francesco Solera,et al.  Learning to Divide and Conquer for Online Multi-target Tracking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[8]  Loic Fagot-Bouquet,et al.  Online multi-person tracking based on global sparse collaborative representations , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[9]  Konrad Schindler,et al.  Online Multi-Target Tracking Using Recurrent Neural Networks , 2016, AAAI.

[10]  A. Cohen.  Truncated and Censored Samples: Theory and Applications , 1991 .

[11]  Luc Van Gool,et al.  Efficient Non-Maximum Suppression , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  T. Westerlund,et al.  Remarks on "Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems" , 1980 .

[14]  Rainer Stiefelhagen,et al.  Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics , 2008, EURASIP J. Image Video Process..

[15]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[16]  Stefan Roth,et al.  People-tracking-by-detection and people-detection-by-tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  D.E. Clark,et al.  An Efficient Track Management Scheme for the Gaussian-Mixture Probability Hypothesis Density Tracker , 2006, 2006 Fourth International Conference on Intelligent Sensing and Information Processing.

[18]  Fabio Tozeto Ramos,et al.  Simple online and realtime tracking , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[19]  Ian D. Reid,et al.  Stable multi-target tracking in real-time surveillance video , 2011, CVPR 2011.

[20]  P. Daras,et al.  Using Tobit Kalman filtering in order to improve the motion recorded by Microsoft Kinect , 2017 .

[21]  Samuel Murray,et al.  Real-Time Multiple Object Tracking - A Study on the Importance of Speed , 2017, ArXiv.

[22]  Ram Nevatia,et al.  Learning to associate: HybridBoosted multi-target tracker for crowded scene , 2009, CVPR.

[23]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[24]  Andrew Harvey,et al.  Forecasting, Structural Time Series Models and the Kalman Filter , 1990 .

[25]  D. Helsel.  Nondetects and data analysis : statistics for censored environmental data , 2005 .

[26]  Bethany Allik,et al.  The Tobit Kalman filter: An estimator for censored data , 2014 .

[27]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[28]  Young-min Song,et al.  Online multiple object tracking with the hierarchically adopted GM-PHD filter using motion and appearance , 2016, 2016 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia).

[29]  R. Jonker,et al.  Improving the Hungarian assignment algorithm , 1986 .

[30]  Bonhwa Ku,et al.  Online multi-object tracking with efficient track drift and fragmentation handling. , 2017, Journal of the Optical Society of America. A, Optics, image science, and vision.

[31]  M. Bernardine Dias,et al.  The Dynamic Hungarian Algorithm for the Assignment Problem with Changing Costs , 2007 .