People Tracking using Laser Range Scanners and Vision

Tracking multiple crossing people is a great challenge, since common algorithms tend to loose some of the persons or to interchange their identities when they get close to each other and split up again. In several consecutive papers it was possible to develop an algorithm using data from laser range scanners which is able to track an arbitrary number of crossing people without any loss of track. In this paper we address the problem of rediscovering the identities of the persons after a crossing. Therefore, a camera system is applied. An infrared camera detects the people in the observation area and then a charge–coupled device camera is used to extract the colour information about those people. For the representation of the colour information the HSV colour space is applied using a histogram. Before the crossing the system learns the mean and the standard deviation of the colour distribution of each person. After the crossing the system relocates the identities by comparing the actually measured colour distributions with the distributions learnt before the crossing. Thereby, a Gaussian distribution of the colour values is assumed. The most probably assignment of the identities is then found using Munkres’ Hungarian algorithm. It is proven with data from real world experiments that our approach can reassign the identities of the tracked persons stable after a crossing.

[1]  Andreas Kräußling,et al.  A switching algorithm for tracking extended targets , 2005, ICINCO.

[2]  A. Kraussling,et al.  Tracking expanded objects using the Viterbi algorithm , 2004, 2004 2nd International IEEE Conference on 'Intelligent Systems'. Proceedings (IEEE Cat. No.04EX791).

[3]  Erwin Prassler,et al.  Tracking People in a Railway Station During Rush-Hour , 1999, ICVS.

[4]  Dirk Schulz,et al.  Tracking Extended Targets - A Switching Algorithm Versus The SJPDAF , 2006, 2006 9th International Conference on Information Fusion.

[5]  Dirk Schulz,et al.  A Probabilistic Exemplar Approach to Combine Laser and Vision for Person Tracking , 2006, Robotics: Science and Systems.

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

[7]  Kunle Olukotun,et al.  The Information-Form Data Association Filter , 2005, NIPS.

[8]  Wolfram Burgard,et al.  Tracking multiple moving objects with a mobile robot , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Dieter Fox,et al.  Knowledge Compilation Properties of Trees-of-BDDs, Revisited , 2009, IJCAI.

[10]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[11]  M. S. Ryan,et al.  The Viterbi Algorithm 1 1 The Viterbi Algorithm . , 2009 .

[12]  Ajo Fod,et al.  Laser-Based People Tracking , 2002 .

[13]  Ryosuke Shibasaki,et al.  A novel system for tracking pedestrians using multiple single-row laser-range scanners , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[14]  Andreas Kräußling,et al.  Tracking of Extended Crossing Objects Using the Viterbi Algorithm , 2004, ICINCO.

[15]  J. Munkres ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[16]  Marta Marrón Romera,et al.  Tracking multiple and dynamic objects with an extended particle filter and an adapted k-means clustering algorithm , 2004 .

[17]  Huosheng Hu,et al.  People tracking with a mobile robot: a comparison of Kalman and particle filters , 2007 .

[18]  Andreas Kräußling,et al.  Tracking multiple objects using the viterbi algorithm , 2006, ICINCO-RA.

[19]  A. Kraubling,et al.  Tracking Extended Moving Objects with a Mobile Robot , 2006, 2006 3rd International IEEE Conference Intelligent Systems.