Trajectories extracted from an object tracker are a valuable source of information to derive describing parameters for traffic situation analysis. In order to ensure the quality of these parameters, the tracker's output has to be evaluated. This is a challenging task, since the choice of the metrics and the choice of the matching --- of ground truth tracks and the output of the tracker --- influences the results considerably. We present the evaluation of a Kalman-filter based tracker using ground truth data of traffic scenes. The Kalman-Filter is object space based and uses observations obtained from multiple camera views. In the evaluation, a two level approach is employed. The first level assesses the ability to correctly locate the objects. The second one evaluates the consistent identification of objects throughout the scene. Matching of tracks is done using a spatial overlap measure. Subsequently, several metrics are applied, whose properties are outlined. The results for simulated and real traffic data are presented. Finally, the implications of aggregation and normalization of these metrics in order to estimate the algorithm's performance are discussed.
[1]
James E. Black,et al.
A novel method for video tracking performance evaluation
,
2003
.
[2]
F. Porikli.
Trajectory Distance Metric Using Hidden Markov Model Based Representation
,
2004
.
[3]
Michalis E. Zervakis,et al.
A survey of video processing techniques for traffic applications
,
2003,
Image Vis. Comput..
[4]
Sharath Pankanti,et al.
Appearance models for occlusion handling
,
2006,
Image Vis. Comput..
[5]
Roger D. Boyle,et al.
Performance Evaluation Metrics and Statistics for Positional Tracker Evaluation
,
2003,
ICVS.
[6]
Mohan M. Trivedi,et al.
Detecting Moving Shadows: Algorithms and Evaluation
,
2003,
IEEE Trans. Pattern Anal. Mach. Intell..
[7]
A. Senior,et al.
Performance Evaluation of Surveillance Systems Under Varying Conditions
,
2004
.
[8]
Jean-Marc Odobez,et al.
Evaluating Multi-Object Tracking
,
2005,
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.