An algorithm for multiple object trajectory tracking

Most tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework called Hidden Markov Model, where the distribution of the object state at current time instance is estimated based on current and previous observations. However this approach is prone to errors caused by temporal distractions such as occlusion, background clutter and multi-object confusion. In this paper we propose a multiple object tracking algorithm that seeks the optimal state sequence which maximizes the joint state-observation probability. We name this algorithm trajectory tracking since it estimates the state sequence or "trajectory" instead of the current state. The algorithm is capable of tracking multiple objects whose number is unknown and varies during tracking. We introduce an observation model which is composed of the original image, the foreground mask given by background subtraction and the object detection map generated by an object detector The image provides the object appearance information. The foreground mask enables the likelihood computation to consider the multi-object configuration in its entirety. The detection map consists of pixel-wise object detection scores, which drives the tracking algorithm to perform joint inference on both the number of objects and their configurations efficiently.

[1]  Shai Avidan,et al.  Support Vector Tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[3]  Andrew Blake,et al.  A sparse probabilistic learning algorithm for real-time tracking , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[4]  Ingemar J. Cox,et al.  An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Ramakant Nevatia,et al.  Segmentation and tracking of multiple humans in complex situations , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Michael Isard,et al.  BraMBLe: a Bayesian multiple-blob tracker , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  Cordelia Schmid,et al.  Face Detection and Tracking in a Video by Propagating Detection Probabilities , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[9]  Yakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Principles and Techniques , 1995 .

[10]  P. Pérez,et al.  Tracking multiple objects with particle filtering , 2002 .

[11]  Larry S. Davis,et al.  W4S: A real-time system detecting and tracking people in 2 1/2D , 1998, ECCV.

[12]  Andrew Blake,et al.  A Probabilistic Exclusion Principle for Tracking Multiple Objects , 2000, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  Yaakov Bar-Shalom,et al.  Sonar tracking of multiple targets using joint probabilistic data association , 1983 .

[14]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Hai Tao,et al.  A Sampling Algorithm for Tracking Multiple Objects , 1999, Workshop on Vision Algorithms.

[16]  Larry S. Davis,et al.  Hydra: multiple people detection and tracking using silhouettes , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[17]  C. Jauffret,et al.  A formulation of multitarget tracking as an incomplete data problem , 1997, IEEE Transactions on Aerospace and Electronic Systems.