Multi-Camera Multi-Person 3D Space Tracking with MCMC in Surveillance Scenarios

We present an algorithm for the tracking of a variable number of 3D persons in a multi-camera setting with partial field-of-view overlap. The multiobject tracking problem is posed in a Bayesian framework and relies on a joint multi-object state space with individual object states defined in the 3D world. The Reversible Jump Markov Chain Monte Carlo (RJ-MCMC) method is used to efficiently search the state-space and recursively estimate the multi-object configuration. The paper presents several contributions: i) the use and extension of several key features for efficient and reliable tracking (e.g. the use of the MCMC framework for multiple camera multiple object tracking; the use of powerful human detector outputs in the MCMC proposals to automatically initialize/update object tracks); ii) the definition of appropriate prior on the object state, to take into account the effects of 2D image measurement uncertainties on the 3D object state estimation due to depth effects; iii) a simple rectification method aligning people 3D standing direction with 2D image vertical axis, allowing to obtain better object measurements relying on rectangular boxes and integral images; iv) representing objects with multiple reference color histograms, to account for variability in color measurement due to changes in pose, lighting, and importantly multiple camera view points. Experimental results on challenging real-world tracking sequences and situations demonstrate the efficiency of our approach.

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

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

[3]  Andrew Calway,et al.  Tracking Many Objects Using Subordinated Condensation , 2002, BMVC.

[4]  Ramakant Nevatia,et al.  Tracking multiple humans in complex situations , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Frank Dellaert,et al.  MCMC-based particle filtering for tracking a variable number of interacting targets , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Jean-Marc Odobez,et al.  Using particles to track varying numbers of interacting people , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Zhanyi Hu,et al.  Single view metrology from scene constraints , 2005, Image Vis. Comput..

[8]  Jean-Marc Odobez,et al.  Multi-Layer Background Subtraction Based on Color and Texture , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Fatih Murat Porikli,et al.  Human Detection via Classification on Riemannian Manifolds , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Sim Heng Ong,et al.  Probability Hypothesis Density Approach for Multi-camera Multi-object Tracking , 2007, ACCV.

[11]  Justus H. Piater,et al.  Multi-camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration , 2007, ACCV.

[12]  Pascal Fua,et al.  Multicamera People Tracking with a Probabilistic Occupancy Map , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Jian Yao,et al.  Fast human detection from videos using covariance features , 2008, ECCV 2008.

[14]  Jean-Marc Odobez,et al.  Multi-camera 3D person tracking with particle filter in a surveillance environment , 2008, 2008 16th European Signal Processing Conference.