TY - JOUR

T1 - Probabilistic multi-person localisation and tracking in image sequences

AU - Klinger, T.

AU - Rottensteiner, F.

AU - Heipke, C.

N1 - Publisher Copyright: © 2016 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) Copyright: Copyright 2017 Elsevier B.V., All rights reserved.

PY - 2017/5

Y1 - 2017/5

N2 - The localisation and tracking of persons in image sequences in commonly guided by recursive filters. Especially in a multi-object tracking environment, where mutual occlusions are inherent, the predictive model is prone to drift away from the actual target position when not taking context into account. Further, if the image-based observations are imprecise, the trajectory is prone to be updated towards a wrong position. In this work we address both these problems by using a new predictive model on the basis of Gaussian Process Regression, and by using generic object detection, as well as instance-specific classification, for refined localisation. The predictive model takes into account the motion of every tracked pedestrian in the scene and the prediction is executed with respect to the velocities of neighbouring persons. In contrast to existing methods our approach uses a Dynamic Bayesian Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image, are modelled as unknowns. This allows the detection to be corrected before it is incorporated into the recursive filter. Our method is evaluated on a publicly available benchmark dataset and outperforms related methods in terms of geometric precision and tracking accuracy.

AB - The localisation and tracking of persons in image sequences in commonly guided by recursive filters. Especially in a multi-object tracking environment, where mutual occlusions are inherent, the predictive model is prone to drift away from the actual target position when not taking context into account. Further, if the image-based observations are imprecise, the trajectory is prone to be updated towards a wrong position. In this work we address both these problems by using a new predictive model on the basis of Gaussian Process Regression, and by using generic object detection, as well as instance-specific classification, for refined localisation. The predictive model takes into account the motion of every tracked pedestrian in the scene and the prediction is executed with respect to the velocities of neighbouring persons. In contrast to existing methods our approach uses a Dynamic Bayesian Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image, are modelled as unknowns. This allows the detection to be corrected before it is incorporated into the recursive filter. Our method is evaluated on a publicly available benchmark dataset and outperforms related methods in terms of geometric precision and tracking accuracy.

KW - Dynamic Bayesian Network

KW - Gaussian process

KW - Linear programming

KW - Pedestrians

KW - Tracking

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=85008455031&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2016.11.006

DO - 10.1016/j.isprsjprs.2016.11.006

M3 - Article

AN - SCOPUS:85008455031

VL - 127

SP - 73

EP - 88

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -